[
  {
    "input_cost_per_token": 1.0003e-7,
    "output_cost_per_token": 0,
    "max_input_tokens": 512,
    "input_dbu_cost_per_token": 0.000001429,
    "max_tokens": 512,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0,
    "output_vector_size": 1024,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "model_id": "databricks-bge-large-en",
    "model_name": "Databricks Bge Large En",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "max_output_tokens": 0,
    "input_cost_per_million": 0.10003000000000001,
    "output_cost_per_million": 0,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "embedding",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.0000029999900000000002,
    "output_cost_per_token": 0.000015000020000000002,
    "max_input_tokens": 200000,
    "max_output_tokens": 128000,
    "input_dbu_cost_per_token": 0.000042857,
    "max_tokens": 128000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000214286,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "supports_assistant_prefill": true,
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "databricks-claude-3-7-sonnet",
    "model_name": "Databricks Claude 3 7 Sonnet",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 2.9999900000000004,
    "output_cost_per_million": 15.000020000000001,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.00000100002,
    "output_cost_per_token": 0.00000500003,
    "max_input_tokens": 200000,
    "max_output_tokens": 64000,
    "input_dbu_cost_per_token": 0.000014286,
    "max_tokens": 64000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000071429,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "supports_assistant_prefill": true,
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "databricks-claude-haiku-4-5",
    "model_name": "Databricks Claude Haiku 4 5",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 1.0000200000000001,
    "output_cost_per_million": 5.00003,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.000015000020000000002,
    "output_cost_per_token": 0.00007500003000000001,
    "max_input_tokens": 200000,
    "max_output_tokens": 32000,
    "input_dbu_cost_per_token": 0.000214286,
    "max_tokens": 32000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.001071429,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "supports_assistant_prefill": true,
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "databricks-claude-opus-4",
    "model_name": "Databricks Claude Opus 4",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 15.000020000000001,
    "output_cost_per_million": 75.00003000000001,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.000015000020000000002,
    "output_cost_per_token": 0.00007500003000000001,
    "max_input_tokens": 200000,
    "max_output_tokens": 32000,
    "input_dbu_cost_per_token": 0.000214286,
    "max_tokens": 32000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.001071429,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "supports_assistant_prefill": true,
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "databricks-claude-opus-4-1",
    "model_name": "Databricks Claude Opus 4 1",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 15.000020000000001,
    "output_cost_per_million": 75.00003000000001,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.00000500003,
    "output_cost_per_token": 0.000025000010000000002,
    "max_input_tokens": 200000,
    "max_output_tokens": 64000,
    "input_dbu_cost_per_token": 0.000071429,
    "max_tokens": 64000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000357143,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "supports_assistant_prefill": true,
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "supports_output_config": true,
    "model_id": "databricks-claude-opus-4-5",
    "model_name": "Databricks Claude Opus 4 5",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 5.00003,
    "output_cost_per_million": 25.000010000000003,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.0000029999900000000002,
    "output_cost_per_token": 0.000015000020000000002,
    "max_input_tokens": 200000,
    "max_output_tokens": 64000,
    "input_dbu_cost_per_token": 0.000042857,
    "max_tokens": 64000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000214286,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "supports_assistant_prefill": true,
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "databricks-claude-sonnet-4",
    "model_name": "Databricks Claude Sonnet 4",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 2.9999900000000004,
    "output_cost_per_million": 15.000020000000001,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.0000029999900000000002,
    "output_cost_per_token": 0.000015000020000000002,
    "max_input_tokens": 200000,
    "max_output_tokens": 64000,
    "input_dbu_cost_per_token": 0.000042857,
    "max_tokens": 64000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000214286,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "supports_assistant_prefill": true,
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "databricks-claude-sonnet-4-1",
    "model_name": "Databricks Claude Sonnet 4 1",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 2.9999900000000004,
    "output_cost_per_million": 15.000020000000001,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.0000029999900000000002,
    "output_cost_per_token": 0.000015000020000000002,
    "max_input_tokens": 200000,
    "max_output_tokens": 64000,
    "input_dbu_cost_per_token": 0.000042857,
    "max_tokens": 64000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000214286,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "supports_assistant_prefill": true,
    "supports_reasoning": true,
    "supports_tool_choice": true,
    "model_id": "databricks-claude-sonnet-4-5",
    "model_name": "Databricks Claude Sonnet 4 5",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 2.9999900000000004,
    "output_cost_per_million": 15.000020000000001,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 3.0001999999999996e-7,
    "output_cost_per_token": 0.00000249998,
    "max_input_tokens": 1048576,
    "max_output_tokens": 65535,
    "input_dbu_cost_per_token": 0.000004285999999999999,
    "max_tokens": 65535,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000035714,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "supports_tool_choice": true,
    "model_id": "databricks-gemini-2-5-flash",
    "model_name": "Databricks Gemini 2 5 Flash",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.30001999999999995,
    "output_cost_per_million": 2.49998,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "supports_function_calling": true,
    "input_cost_per_token": 0.00000124999,
    "output_cost_per_token": 0.000009999990000000002,
    "max_input_tokens": 1048576,
    "max_output_tokens": 65536,
    "input_dbu_cost_per_token": 0.000017857,
    "max_tokens": 65536,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000142857,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "supports_tool_choice": true,
    "model_id": "databricks-gemini-2-5-pro",
    "model_name": "Databricks Gemini 2 5 Pro",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 1.24999,
    "output_cost_per_million": 9.999990000000002,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 1.5000999999999998e-7,
    "output_cost_per_token": 5.0001e-7,
    "max_input_tokens": 128000,
    "max_output_tokens": 32000,
    "input_dbu_cost_per_token": 0.0000021429999999999996,
    "max_tokens": 32000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000007143,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "model_id": "databricks-gemma-3-12b",
    "model_name": "Databricks Gemma 3 12B",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.15000999999999998,
    "output_cost_per_million": 0.5000100000000001,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 0.00000124999,
    "output_cost_per_token": 0.000009999990000000002,
    "max_input_tokens": 272000,
    "max_output_tokens": 128000,
    "input_dbu_cost_per_token": 0.000017857,
    "max_tokens": 128000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000142857,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "model_id": "databricks-gpt-5",
    "model_name": "Databricks GPT-5",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 1.24999,
    "output_cost_per_million": 9.999990000000002,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 0.00000124999,
    "output_cost_per_token": 0.000009999990000000002,
    "max_input_tokens": 272000,
    "max_output_tokens": 128000,
    "input_dbu_cost_per_token": 0.000017857,
    "max_tokens": 128000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000142857,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "model_id": "databricks-gpt-5-1",
    "model_name": "Databricks GPT-5 1",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 1.24999,
    "output_cost_per_million": 9.999990000000002,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 2.4997000000000006e-7,
    "output_cost_per_token": 0.0000019999700000000004,
    "max_input_tokens": 272000,
    "max_output_tokens": 128000,
    "input_dbu_cost_per_token": 0.000003571,
    "max_tokens": 128000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000028571,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "model_id": "databricks-gpt-5-mini",
    "model_name": "Databricks GPT-5 Mini",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.24997000000000005,
    "output_cost_per_million": 1.9999700000000002,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 4.998e-8,
    "output_cost_per_token": 3.9998000000000007e-7,
    "max_input_tokens": 272000,
    "max_output_tokens": 128000,
    "input_dbu_cost_per_token": 7.14e-7,
    "max_tokens": 128000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000005714000000000001,
    "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving",
    "model_id": "databricks-gpt-5-nano",
    "model_name": "Databricks GPT-5 Nano",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.049980000000000004,
    "output_cost_per_million": 0.39998000000000006,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 1.5000999999999998e-7,
    "output_cost_per_token": 5.9997e-7,
    "max_input_tokens": 131072,
    "max_output_tokens": 131072,
    "input_dbu_cost_per_token": 0.0000021429999999999996,
    "max_tokens": 131072,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000008571,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "model_id": "databricks-gpt-oss-120b",
    "model_name": "Databricks GPT Oss 120B",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.15000999999999998,
    "output_cost_per_million": 0.59997,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 7e-8,
    "output_cost_per_token": 3.0001999999999996e-7,
    "max_input_tokens": 131072,
    "max_output_tokens": 131072,
    "input_dbu_cost_per_token": 0.000001,
    "max_tokens": 131072,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000004285999999999999,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "model_id": "databricks-gpt-oss-20b",
    "model_name": "Databricks GPT Oss 20B",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.07,
    "output_cost_per_million": 0.30001999999999995,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 1.2999000000000001e-7,
    "output_cost_per_token": 0,
    "max_input_tokens": 8192,
    "input_dbu_cost_per_token": 0.000001857,
    "max_tokens": 8192,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0,
    "output_vector_size": 1024,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "model_id": "databricks-gte-large-en",
    "model_name": "Databricks Gte Large En",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "max_output_tokens": 0,
    "input_cost_per_million": 0.12999000000000002,
    "output_cost_per_million": 0,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "embedding",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 5.0001e-7,
    "output_cost_per_token": 0.0000015000300000000002,
    "max_input_tokens": 4096,
    "max_output_tokens": 4096,
    "input_dbu_cost_per_token": 0.000007143,
    "max_tokens": 4096,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000021429,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "supports_tool_choice": true,
    "model_id": "databricks-llama-2-70b-chat",
    "model_name": "Databricks Llama 2 70B Chat",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.5000100000000001,
    "output_cost_per_million": 1.5000300000000002,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 5.0001e-7,
    "output_cost_per_token": 0.0000015000300000000002,
    "max_input_tokens": 128000,
    "max_output_tokens": 128000,
    "input_dbu_cost_per_token": 0.000007143,
    "max_tokens": 128000,
    "metadata": {
      "notes": "Databricks documentation now provides both DBU costs (_dbu_cost_per_token) and dollar costs(_cost_per_token)."
    },
    "output_dbu_cost_per_token": 0.000021429,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "supports_tool_choice": true,
    "model_id": "databricks-llama-4-maverick",
    "model_name": "Databricks Llama 4 Maverick",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.5000100000000001,
    "output_cost_per_million": 1.5000300000000002,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 0.00000500003,
    "output_cost_per_token": 0.000015000020000000002,
    "max_input_tokens": 128000,
    "max_output_tokens": 128000,
    "input_dbu_cost_per_token": 0.000071429,
    "max_tokens": 128000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000214286,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "supports_tool_choice": true,
    "model_id": "databricks-meta-llama-3-1-405b-instruct",
    "model_name": "Databricks Meta Llama 3 1 405B Instruct",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 5.00003,
    "output_cost_per_million": 15.000020000000001,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 1.5000999999999998e-7,
    "output_cost_per_token": 4.5003000000000007e-7,
    "max_input_tokens": 200000,
    "max_output_tokens": 128000,
    "input_dbu_cost_per_token": 0.0000021429999999999996,
    "max_tokens": 128000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000006429000000000001,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "model_id": "databricks-meta-llama-3-1-8b-instruct",
    "model_name": "Databricks Meta Llama 3 1 8B Instruct",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.15000999999999998,
    "output_cost_per_million": 0.45003000000000004,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 5.0001e-7,
    "output_cost_per_token": 0.0000015000300000000002,
    "max_input_tokens": 128000,
    "max_output_tokens": 128000,
    "input_dbu_cost_per_token": 0.000007143,
    "max_tokens": 128000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000021429,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "supports_tool_choice": true,
    "model_id": "databricks-meta-llama-3-3-70b-instruct",
    "model_name": "Databricks Meta Llama 3 3 70B Instruct",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.5000100000000001,
    "output_cost_per_million": 1.5000300000000002,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 0.00000100002,
    "output_cost_per_token": 0.0000029999900000000002,
    "max_input_tokens": 128000,
    "max_output_tokens": 128000,
    "input_dbu_cost_per_token": 0.000014286,
    "max_tokens": 128000,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000042857,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "supports_tool_choice": true,
    "model_id": "databricks-meta-llama-3-70b-instruct",
    "model_name": "Databricks Meta Llama 3 70B Instruct",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 1.0000200000000001,
    "output_cost_per_million": 2.9999900000000004,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 5.0001e-7,
    "output_cost_per_token": 0.00000100002,
    "max_input_tokens": 4096,
    "max_output_tokens": 4096,
    "input_dbu_cost_per_token": 0.000007143,
    "max_tokens": 4096,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000014286,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "supports_tool_choice": true,
    "model_id": "databricks-mixtral-8x7b-instruct",
    "model_name": "Databricks Mixtral 8x7B Instruct",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.5000100000000001,
    "output_cost_per_million": 1.0000200000000001,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 0.00000100002,
    "output_cost_per_token": 0.00000100002,
    "max_input_tokens": 8192,
    "max_output_tokens": 8192,
    "input_dbu_cost_per_token": 0.000014286,
    "max_tokens": 8192,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0.000014286,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "supports_tool_choice": true,
    "model_id": "databricks-mpt-30b-instruct",
    "model_name": "Databricks Mpt 30B Instruct",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 1.0000200000000001,
    "output_cost_per_million": 1.0000200000000001,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  },
  {
    "input_cost_per_token": 5.0001e-7,
    "output_cost_per_token": 0,
    "max_input_tokens": 8192,
    "max_output_tokens": 8192,
    "input_dbu_cost_per_token": 0.000007143,
    "max_tokens": 8192,
    "metadata": {
      "notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."
    },
    "output_dbu_cost_per_token": 0,
    "source": "https://www.databricks.com/product/pricing/foundation-model-serving",
    "supports_tool_choice": true,
    "model_id": "databricks-mpt-7b-instruct",
    "model_name": "Databricks Mpt 7B Instruct",
    "provider_id": "databricks",
    "provider_name": "Databricks",
    "input_cost_per_million": 0.5000100000000001,
    "output_cost_per_million": 0,
    "cache_read_cost_per_token": 0,
    "cache_read_cost_per_million": 0,
    "cache_write_cost_per_token": 0,
    "cache_write_cost_per_million": 0,
    "model_type": "chat",
    "deprecation_date": null,
    "supports_function_calling": false,
    "supports_vision": false,
    "supports_json_mode": false,
    "supports_parallel_functions": false
  }
]