603 lines
15 KiB
JSON
603 lines
15 KiB
JSON
{
|
|
"schema_version": "1.0",
|
|
"models": {
|
|
"BAAI/bge-en-icl": {
|
|
"mode": "embedding",
|
|
"context_window": {
|
|
"max_input": 32768,
|
|
"max_tokens": 32768
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.01,
|
|
"output_per_million_tokens": 0.0
|
|
},
|
|
"capabilities": {
|
|
"function_calling": false,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"BAAI/bge-multilingual-gemma2": {
|
|
"mode": "embedding",
|
|
"context_window": {
|
|
"max_input": 8192,
|
|
"max_tokens": 8192
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.01,
|
|
"output_per_million_tokens": 0.0
|
|
},
|
|
"capabilities": {
|
|
"function_calling": false,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"NousResearch/Hermes-3-Llama-3.1-405B": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 1.0,
|
|
"output_per_million_tokens": 3.0
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/QwQ-32B": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 32768,
|
|
"max_output": 32768,
|
|
"max_tokens": 32768
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.15,
|
|
"output_per_million_tokens": 0.45
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": true,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen2-VL-72B-Instruct": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 131072,
|
|
"max_output": 131072,
|
|
"max_tokens": 131072
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.13,
|
|
"output_per_million_tokens": 0.4
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": true,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen2-VL-7B-Instruct": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 131072,
|
|
"max_output": 131072,
|
|
"max_tokens": 131072
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.02,
|
|
"output_per_million_tokens": 0.06
|
|
},
|
|
"capabilities": {
|
|
"function_calling": false,
|
|
"vision": true,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen2.5-32B-Instruct": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.06,
|
|
"output_per_million_tokens": 0.2
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen2.5-72B-Instruct": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.13,
|
|
"output_per_million_tokens": 0.4
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen2.5-Coder-7B": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 32768,
|
|
"max_output": 32768,
|
|
"max_tokens": 32768
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.01,
|
|
"output_per_million_tokens": 0.03
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen2.5-VL-72B-Instruct": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 131072,
|
|
"max_output": 131072,
|
|
"max_tokens": 131072
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.13,
|
|
"output_per_million_tokens": 0.4
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": true,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen3-14B": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 32768,
|
|
"max_output": 32768,
|
|
"max_tokens": 32768
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.08,
|
|
"output_per_million_tokens": 0.24
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen3-235B-A22B": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 262144,
|
|
"max_output": 262144,
|
|
"max_tokens": 262144
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.2,
|
|
"output_per_million_tokens": 0.6
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen3-30B-A3B": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 32768,
|
|
"max_output": 32768,
|
|
"max_tokens": 32768
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.1,
|
|
"output_per_million_tokens": 0.3
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen3-32B": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 32768,
|
|
"max_output": 32768,
|
|
"max_tokens": 32768
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.1,
|
|
"output_per_million_tokens": 0.3
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"Qwen/Qwen3-4B": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 32768,
|
|
"max_output": 32768,
|
|
"max_tokens": 32768
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.08,
|
|
"output_per_million_tokens": 0.24
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"deepseek-ai/DeepSeek-R1": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.8,
|
|
"output_per_million_tokens": 2.4
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": true,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"deepseek-ai/DeepSeek-R1-0528": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 164000,
|
|
"max_output": 164000,
|
|
"max_tokens": 164000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.8,
|
|
"output_per_million_tokens": 2.4
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": true,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.25,
|
|
"output_per_million_tokens": 0.75
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"deepseek-ai/DeepSeek-V3": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.5,
|
|
"output_per_million_tokens": 1.5
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"deepseek-ai/DeepSeek-V3-0324": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.5,
|
|
"output_per_million_tokens": 1.5
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"google/gemma-3-27b-it": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.06,
|
|
"output_per_million_tokens": 0.2
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": true,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"intfloat/e5-mistral-7b-instruct": {
|
|
"mode": "embedding",
|
|
"context_window": {
|
|
"max_input": 32768,
|
|
"max_tokens": 32768
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.01,
|
|
"output_per_million_tokens": 0.0
|
|
},
|
|
"capabilities": {
|
|
"function_calling": false,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"meta-llama/Llama-3.3-70B-Instruct": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.13,
|
|
"output_per_million_tokens": 0.4
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"meta-llama/Llama-Guard-3-8B": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.02,
|
|
"output_per_million_tokens": 0.06
|
|
},
|
|
"capabilities": {
|
|
"function_calling": false,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"meta-llama/Meta-Llama-3.1-405B-Instruct": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 1.0,
|
|
"output_per_million_tokens": 3.0
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"meta-llama/Meta-Llama-3.1-70B-Instruct": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.13,
|
|
"output_per_million_tokens": 0.4
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"meta-llama/Meta-Llama-3.1-8B-Instruct": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.02,
|
|
"output_per_million_tokens": 0.06
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"mistralai/Mistral-Nemo-Instruct-2407": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.04,
|
|
"output_per_million_tokens": 0.12
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 128000,
|
|
"max_output": 128000,
|
|
"max_tokens": 128000
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.6,
|
|
"output_per_million_tokens": 1.8
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
},
|
|
"nvidia/Llama-3.3-Nemotron-Super-49B-v1": {
|
|
"mode": "chat",
|
|
"context_window": {
|
|
"max_input": 131072,
|
|
"max_output": 131072,
|
|
"max_tokens": 131072
|
|
},
|
|
"pricing": {
|
|
"input_per_million_tokens": 0.1,
|
|
"output_per_million_tokens": 0.4
|
|
},
|
|
"capabilities": {
|
|
"function_calling": true,
|
|
"vision": false,
|
|
"reasoning": false,
|
|
"prompt_caching": false,
|
|
"response_schema": false
|
|
},
|
|
"last_updated_at": "2026-04-24"
|
|
}
|
|
}
|
|
}
|