{ "schema_version": "1.0", "models": { "databricks-bge-large-en": { "mode": "embedding", "context_window": { "max_input": 512, "max_tokens": 512 }, "pricing": { "input_per_million_tokens": 0.10003, "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" }, "databricks-claude-3-7-sonnet": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 2.99999, "output_per_million_tokens": 15.00002 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-claude-haiku-4-5": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 1.00002, "output_per_million_tokens": 5.00003 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-claude-opus-4": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 32000, "max_tokens": 32000 }, "pricing": { "input_per_million_tokens": 15.00002, "output_per_million_tokens": 75.00003 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-claude-opus-4-1": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 32000, "max_tokens": 32000 }, "pricing": { "input_per_million_tokens": 15.00002, "output_per_million_tokens": 75.00003 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-claude-opus-4-5": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 5.00003, "output_per_million_tokens": 25.00001 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-claude-opus-4-6": { "mode": "chat", "context_window": { "max_input": 1000000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 5.00003, "output_per_million_tokens": 25.00001, "cache_write_per_million_tokens": 6.25004, "cache_read_per_million_tokens": 0.5 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-claude-opus-4-6[1m]": { "mode": "chat", "context_window": { "max_input": 1000000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 5.00003, "output_per_million_tokens": 25.00001, "cache_write_per_million_tokens": 6.25004, "cache_read_per_million_tokens": 0.5 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-claude-opus-4-7": { "mode": "chat", "context_window": { "max_input": 1000000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 5.00003, "output_per_million_tokens": 25.00001, "cache_write_per_million_tokens": 6.25004, "cache_read_per_million_tokens": 0.5 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-claude-opus-4-7[1m]": { "mode": "chat", "context_window": { "max_input": 1000000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 5.00003, "output_per_million_tokens": 25.00001, "cache_write_per_million_tokens": 6.25004, "cache_read_per_million_tokens": 0.5 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-claude-sonnet-4": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 2.99999, "output_per_million_tokens": 15.00002 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-claude-sonnet-4-1": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 2.99999, "output_per_million_tokens": 15.00002 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-claude-sonnet-4-5": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 2.99999, "output_per_million_tokens": 15.00002 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-claude-sonnet-4-6": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 2.99999, "output_per_million_tokens": 15.00002, "cache_write_per_million_tokens": 3.74999, "cache_read_per_million_tokens": 0.3 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-claude-sonnet-4-6[1m]": { "mode": "chat", "context_window": { "max_input": 1000000, "max_output": 64000, "max_tokens": 64000 }, "pricing": { "input_per_million_tokens": 2.99999, "output_per_million_tokens": 15.00002, "cache_write_per_million_tokens": 3.74999, "cache_read_per_million_tokens": 0.3 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gemini-2-5-flash": { "mode": "chat", "context_window": { "max_input": 1048576, "max_output": 65535, "max_tokens": 65535 }, "pricing": { "input_per_million_tokens": 0.30002, "output_per_million_tokens": 2.49998 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-gemini-2-5-pro": { "mode": "chat", "context_window": { "max_input": 1048576, "max_output": 65536, "max_tokens": 65536 }, "pricing": { "input_per_million_tokens": 1.24999, "output_per_million_tokens": 9.99999 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-gemini-3-1-flash-lite": { "mode": "chat", "context_window": { "max_input": 1048576, "max_output": 65535, "max_tokens": 65535 }, "pricing": { "input_per_million_tokens": 0.31248, "output_per_million_tokens": 1.87502, "cache_write_per_million_tokens": 0.31248, "cache_read_per_million_tokens": 0.03125 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gemini-3-1-pro": { "mode": "chat", "context_window": { "max_input": 1048576, "max_output": 65536, "max_tokens": 65536 }, "pricing": { "input_per_million_tokens": 2.49998, "output_per_million_tokens": 15.00002, "cache_write_per_million_tokens": 2.49998, "cache_read_per_million_tokens": 0.25 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gemini-3-5-flash": { "mode": "chat", "context_window": { "max_input": 1048576, "max_output": 65535, "max_tokens": 65535 }, "pricing": { "input_per_million_tokens": 1.87502, "output_per_million_tokens": 11.24998, "cache_write_per_million_tokens": 1.87502, "cache_read_per_million_tokens": 0.1875 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gemini-3-flash": { "mode": "chat", "context_window": { "max_input": 1048576, "max_output": 65535, "max_tokens": 65535 }, "pricing": { "input_per_million_tokens": 0.62503, "output_per_million_tokens": 3.74997, "cache_write_per_million_tokens": 0.62503, "cache_read_per_million_tokens": 0.0625 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": false, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gemini-3-pro": { "mode": "chat", "context_window": { "max_input": 1048576, "max_output": 65536, "max_tokens": 65536 }, "pricing": { "input_per_million_tokens": 2.49998, "output_per_million_tokens": 15.00002, "cache_write_per_million_tokens": 2.49998, "cache_read_per_million_tokens": 0.25 }, "capabilities": { "function_calling": true, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gemma-3-12b": { "mode": "chat", "context_window": { "max_input": 128000, "max_output": 32000, "max_tokens": 32000 }, "pricing": { "input_per_million_tokens": 0.15001, "output_per_million_tokens": 0.50001 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-gpt-5": { "mode": "chat", "context_window": { "max_input": 272000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 1.24999, "output_per_million_tokens": 9.99999 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-gpt-5-1": { "mode": "chat", "context_window": { "max_input": 272000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 1.24999, "output_per_million_tokens": 9.99999 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-gpt-5-1-codex-max": { "mode": "chat", "context_window": { "max_input": 400000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 1.24999, "output_per_million_tokens": 9.99999, "cache_write_per_million_tokens": 1.24999, "cache_read_per_million_tokens": 0.125 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gpt-5-1-codex-mini": { "mode": "chat", "context_window": { "max_input": 400000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 0.24997, "output_per_million_tokens": 1.99997, "cache_write_per_million_tokens": 0.24997, "cache_read_per_million_tokens": 0.025 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gpt-5-2": { "mode": "chat", "context_window": { "max_input": 400000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 1.75, "output_per_million_tokens": 14.0, "cache_write_per_million_tokens": 1.75, "cache_read_per_million_tokens": 0.175 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gpt-5-2-codex": { "mode": "chat", "context_window": { "max_input": 400000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 1.75, "output_per_million_tokens": 14.0, "cache_write_per_million_tokens": 1.75, "cache_read_per_million_tokens": 0.175 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gpt-5-3-codex": { "mode": "chat", "context_window": { "max_input": 400000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 1.75, "output_per_million_tokens": 14.0, "cache_write_per_million_tokens": 1.75, "cache_read_per_million_tokens": 0.175 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gpt-5-4": { "mode": "chat", "context_window": { "max_input": 400000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 2.49998, "output_per_million_tokens": 15.00002, "cache_write_per_million_tokens": 2.49998, "cache_read_per_million_tokens": 0.25 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gpt-5-4-mini": { "mode": "chat", "context_window": { "max_input": 400000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 0.74998, "output_per_million_tokens": 4.50002, "cache_write_per_million_tokens": 0.74998, "cache_read_per_million_tokens": 0.075 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gpt-5-4-nano": { "mode": "chat", "context_window": { "max_input": 400000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 0.19999, "output_per_million_tokens": 1.24999, "cache_write_per_million_tokens": 0.19999, "cache_read_per_million_tokens": 0.02 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gpt-5-5": { "mode": "chat", "context_window": { "max_input": 400000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 5.00003, "output_per_million_tokens": 30.00003, "cache_write_per_million_tokens": 5.00003, "cache_read_per_million_tokens": 0.5 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gpt-5-5-pro": { "mode": "chat", "context_window": { "max_input": 400000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 30.00003, "output_per_million_tokens": 180.00003, "cache_write_per_million_tokens": 30.00003, "cache_read_per_million_tokens": 3.0 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": true, "prompt_caching": true, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-gpt-5-mini": { "mode": "chat", "context_window": { "max_input": 272000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 0.24997, "output_per_million_tokens": 1.99997 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-gpt-5-nano": { "mode": "chat", "context_window": { "max_input": 272000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 0.04998, "output_per_million_tokens": 0.39998 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-06-12" }, "databricks-gpt-oss-120b": { "mode": "chat", "context_window": { "max_input": 131072, "max_output": 131072, "max_tokens": 131072 }, "pricing": { "input_per_million_tokens": 0.15001, "output_per_million_tokens": 0.59997 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-gpt-oss-20b": { "mode": "chat", "context_window": { "max_input": 131072, "max_output": 131072, "max_tokens": 131072 }, "pricing": { "input_per_million_tokens": 0.07, "output_per_million_tokens": 0.30002 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-gte-large-en": { "mode": "embedding", "context_window": { "max_input": 8192, "max_tokens": 8192 }, "pricing": { "input_per_million_tokens": 0.12999, "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" }, "databricks-llama-2-70b-chat": { "mode": "chat", "context_window": { "max_input": 4096, "max_output": 4096, "max_tokens": 4096 }, "pricing": { "input_per_million_tokens": 0.50001, "output_per_million_tokens": 1.50003 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-llama-4-maverick": { "mode": "chat", "context_window": { "max_input": 128000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 0.50001, "output_per_million_tokens": 1.50003 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-meta-llama-3-1-405b-instruct": { "mode": "chat", "context_window": { "max_input": 128000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 5.00003, "output_per_million_tokens": 15.00002 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-meta-llama-3-1-8b-instruct": { "mode": "chat", "context_window": { "max_input": 200000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 0.15001, "output_per_million_tokens": 0.45003 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-meta-llama-3-3-70b-instruct": { "mode": "chat", "context_window": { "max_input": 128000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 0.50001, "output_per_million_tokens": 1.50003 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-meta-llama-3-70b-instruct": { "mode": "chat", "context_window": { "max_input": 128000, "max_output": 128000, "max_tokens": 128000 }, "pricing": { "input_per_million_tokens": 1.00002, "output_per_million_tokens": 2.99999 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-mixtral-8x7b-instruct": { "mode": "chat", "context_window": { "max_input": 4096, "max_output": 4096, "max_tokens": 4096 }, "pricing": { "input_per_million_tokens": 0.50001, "output_per_million_tokens": 1.00002 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-mpt-30b-instruct": { "mode": "chat", "context_window": { "max_input": 8192, "max_output": 8192, "max_tokens": 8192 }, "pricing": { "input_per_million_tokens": 1.00002, "output_per_million_tokens": 1.00002 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-04-24" }, "databricks-mpt-7b-instruct": { "mode": "chat", "context_window": { "max_input": 8192, "max_output": 8192, "max_tokens": 8192 }, "pricing": { "input_per_million_tokens": 0.50001, "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" }, "databricks-qwen3-embedding-0-6b": { "mode": "embedding", "context_window": { "max_input": 32000, "max_tokens": 32000 }, "pricing": { "input_per_million_tokens": 0.02002, "output_per_million_tokens": 0.0 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-qwen3-next-80b-a3b-instruct": { "mode": "chat", "context_window": { "max_input": 131072, "max_output": 32768, "max_tokens": 32768 }, "pricing": { "input_per_million_tokens": 0.15001, "output_per_million_tokens": 1.20001 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": false, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-05-20" }, "databricks-qwen35-122b-a10b": { "mode": "chat", "context_window": { "max_input": 256000, "max_output": 8000, "max_tokens": 8000 }, "pricing": { "input_per_million_tokens": 0.15001, "output_per_million_tokens": 0.50001 }, "capabilities": { "function_calling": false, "vision": false, "reasoning": true, "prompt_caching": false, "response_schema": false }, "last_updated_at": "2026-05-20" } } }