diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 616d58970cf..7304ca04eb5 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -5311,7 +5311,7 @@ "cache_read_input_token_cost": 4e-06, "deprecation_date": "2027-03-02", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5344,7 +5344,7 @@ "cache_read_input_token_cost": 4e-06, "deprecation_date": "2027-08-24", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5372,11 +5372,115 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "azure/gpt-realtime-2": { + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2026-08-31", + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 2.4e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-realtime-2.1": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-06-25", + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 2.4e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-realtime-2.1-mini": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2027-06-25", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_image_token": 8e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "azure/gpt-realtime-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5408,7 +5512,7 @@ "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -16995,6 +17099,7 @@ "databricks/databricks-claude-3-7-sonnet": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, + "deprecation_date": "2026-04-12", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -17042,6 +17147,35 @@ "supports_vision": false, "thinking_always_on": true }, + "databricks/databricks-claude-fable-5-1": { + "cache_creation_input_token_cost": 1.250004e-05, + "cache_read_input_token_cost": 2.5004e-07, + "input_cost_per_token": 1.000006e-05, + "input_dbu_cost_per_token": 0.000142858, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.000002e-05, + "output_dbu_cost_per_token": 0.000714286, + "prompt_cache_min_tokens": 512, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, "databricks/databricks-claude-haiku-4-5": { "cache_creation_input_token_cost": 1.24999e-06, "cache_read_input_token_cost": 1.0003e-07, @@ -17242,6 +17376,7 @@ "databricks/databricks-claude-sonnet-4": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, + "deprecation_date": "2026-10-09", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -17254,13 +17389,13 @@ "mode": "chat", "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, + "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "prompt_cache_min_tokens": 1024 + "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-1": { "cache_creation_input_token_cost": 3.74997e-06, @@ -17417,6 +17552,7 @@ "databricks/databricks-gemini-2-5-flash": { "cache_creation_input_token_cost": 3.0002e-07, "cache_read_input_token_cost": 3.0002e-08, + "deprecation_date": "2026-10-02", "input_cost_per_token": 3.0001999999999996e-07, "input_dbu_cost_per_token": 4.285999999999999e-06, "litellm_provider": "databricks", @@ -17474,6 +17610,48 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "databricks/databricks-gemini-3-1-flash-image": { + "litellm_provider": "databricks", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, + "databricks/databricks-gemini-3-pro-image": { + "litellm_provider": "databricks", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, "databricks/databricks-gemini-3-1-pro": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, @@ -17534,6 +17712,148 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "databricks/databricks-gemini-3-8-flash": { + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-7-flash": { + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-6-flash": { + "cache_creation_input_token_cost": 1.87502e-06, + "cache_read_input_token_cost": 1.8753e-07, + "input_cost_per_token": 1.87502e-06, + "input_dbu_cost_per_token": 2.6786e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 9.37503e-06, + "output_dbu_cost_per_token": 0.000133929, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-5-flash": { + "cache_creation_input_token_cost": 1.87502e-06, + "cache_read_input_token_cost": 1.8753e-07, + "input_cost_per_token": 1.87502e-06, + "input_dbu_cost_per_token": 2.6786e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.124998e-05, + "output_dbu_cost_per_token": 0.000160714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-5-flash-lite": { + "cache_creation_input_token_cost": 3.7499e-07, + "cache_read_input_token_cost": 3.752e-08, + "input_cost_per_token": 3.7499e-07, + "input_dbu_cost_per_token": 5.357e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 3.12501e-06, + "output_dbu_cost_per_token": 4.4643e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, @@ -17579,16 +17899,53 @@ "supports_tool_choice": true, "supports_vision": false }, + "databricks/databricks-glm-5-3": { + "cache_creation_input_token_cost": 1.4e-06, + "cache_read_input_token_cost": 2.5998e-07, + "input_cost_per_token": 1.4e-06, + "input_dbu_cost_per_token": 2e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 4.39999e-06, + "output_dbu_cost_per_token": 6.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, "databricks/databricks-glm-5-3-flash": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 3.003e-08, + "input_cost_per_token": 1.5001e-07, + "input_dbu_cost_per_token": 2.143e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "metadata": { - "notes": "Databricks has not published pay-per-token DBU rates for this model yet (not on the foundation-model-serving pricing page as of 2026-08-27), so cost fields are omitted until rates are published." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "output_cost_per_token": 5.0001e-07, + "output_dbu_cost_per_token": 7.143e-06, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" @@ -17600,7 +17957,8 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "thinking_always_on": true }, "databricks/databricks-gpt-5": { "cache_creation_input_token_cost": 1.24999e-06, @@ -17618,7 +17976,9 @@ "output_cost_per_token": 9.999990000000002e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-1": { "cache_creation_input_token_cost": 1.24999e-06, @@ -17636,11 +17996,14 @@ "output_cost_per_token": 9.999990000000002e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-1-codex-max": { "cache_creation_input_token_cost": 1.24999e-06, "cache_read_input_token_cost": 1.2502e-07, + "deprecation_date": "2026-07-16", "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", @@ -17659,6 +18022,7 @@ "databricks/databricks-gpt-5-1-codex-mini": { "cache_creation_input_token_cost": 2.4997e-07, "cache_read_input_token_cost": 2.499e-08, + "deprecation_date": "2026-07-16", "input_cost_per_token": 2.4997e-07, "input_dbu_cost_per_token": 3.571e-06, "litellm_provider": "databricks", @@ -17690,11 +18054,14 @@ "output_cost_per_token": 1.4e-05, "output_dbu_cost_per_token": 0.0002, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-2-codex": { "cache_creation_input_token_cost": 1.75e-06, "cache_read_input_token_cost": 1.75e-07, + "deprecation_date": "2026-07-16", "input_cost_per_token": 1.75e-06, "input_dbu_cost_per_token": 2.5e-05, "litellm_provider": "databricks", @@ -17726,7 +18093,9 @@ "output_cost_per_token": 1.4e-05, "output_dbu_cost_per_token": 0.0002, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-4": { "cache_creation_input_token_cost": 2.49998e-06, @@ -17734,7 +18103,7 @@ "input_cost_per_token": 2.49998e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { @@ -17744,7 +18113,18 @@ "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-4-mini": { "cache_creation_input_token_cost": 7.4998e-07, @@ -17762,7 +18142,18 @@ "output_cost_per_token": 4.50002e-06, "output_dbu_cost_per_token": 6.4286e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-4-nano": { "cache_creation_input_token_cost": 1.9999e-07, @@ -17780,7 +18171,163 @@ "output_cost_per_token": 1.24999e-06, "output_dbu_cost_per_token": 1.7857e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-sol": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 3.9998e-07, + "input_cost_per_token": 4.00001e-06, + "input_dbu_cost_per_token": 5.7143e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." + }, + "mode": "chat", + "output_cost_per_token": 1.999998e-05, + "output_dbu_cost_per_token": 0.000285714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-terra": { + "cache_creation_input_token_cost": 3.12501e-06, + "cache_read_input_token_cost": 2.4997e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-luna": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_read_input_token_cost": 1.0003e-07, + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.99998e-06, + "output_dbu_cost_per_token": 8.5714e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-5": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 5.0001e-07, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 2.999997e-05, + "output_dbu_cost_per_token": 0.000428571, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-5-pro": { + "cache_creation_input_token_cost": 2.999997e-05, + "cache_read_input_token_cost": 2.999997e-05, + "input_cost_per_token": 2.999997e-05, + "input_dbu_cost_per_token": 0.000428571, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 0.00018000003, + "output_dbu_cost_per_token": 0.002571429, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-mini": { "cache_creation_input_token_cost": 2.4997e-07, @@ -17798,7 +18345,9 @@ "output_cost_per_token": 1.9999700000000004e-06, "output_dbu_cost_per_token": 2.8571e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-nano": { "cache_creation_input_token_cost": 4.998e-08, @@ -17816,7 +18365,9 @@ "output_cost_per_token": 3.9998000000000007e-07, "output_dbu_cost_per_token": 5.714000000000001e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-oss-120b": { "cache_creation_input_token_cost": 1.5001e-07, @@ -17852,6 +18403,32 @@ "output_dbu_cost_per_token": 4.285999999999999e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-grok-4-6": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 6.2503e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 500000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 7.50001e-06, + "output_dbu_cost_per_token": 0.000107143, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "databricks/databricks-gte-large-en": { "cache_creation_input_token_cost": 1.2999e-07, "cache_read_input_token_cost": 1.2999e-07, @@ -17869,6 +18446,34 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-inkling": { + "cache_creation_input_token_cost": 1.00002e-06, + "cache_read_input_token_cost": 1.7003e-07, + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 4.04999e-06, + "output_dbu_cost_per_token": 5.7857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, "databricks/databricks-kimi-k3": { "cache_creation_input_token_cost": 2.99999e-06, "cache_read_input_token_cost": 3.0002e-07, @@ -17901,6 +18506,7 @@ "databricks/databricks-llama-2-70b-chat": { "cache_creation_input_token_cost": 5.0001e-07, "cache_read_input_token_cost": 5.0001e-07, + "deprecation_date": "2024-10-30", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -17937,6 +18543,7 @@ "databricks/databricks-meta-llama-3-1-405b-instruct": { "cache_creation_input_token_cost": 5.00003e-06, "cache_read_input_token_cost": 5.00003e-06, + "deprecation_date": "2026-02-15", "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", @@ -17990,6 +18597,7 @@ "databricks/databricks-meta-llama-3-70b-instruct": { "cache_creation_input_token_cost": 1.00002e-06, "cache_read_input_token_cost": 1.00002e-06, + "deprecation_date": "2024-07-23", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -18008,6 +18616,7 @@ "databricks/databricks-mixtral-8x7b-instruct": { "cache_creation_input_token_cost": 5.0001e-07, "cache_read_input_token_cost": 5.0001e-07, + "deprecation_date": "2025-04-30", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -18026,6 +18635,7 @@ "databricks/databricks-mpt-30b-instruct": { "cache_creation_input_token_cost": 1.00002e-06, "cache_read_input_token_cost": 1.00002e-06, + "deprecation_date": "2024-08-30", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -18044,6 +18654,7 @@ "databricks/databricks-mpt-7b-instruct": { "cache_creation_input_token_cost": 5.0001e-07, "cache_read_input_token_cost": 5.0001e-07, + "deprecation_date": "2024-08-30", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -18059,6 +18670,74 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, + "databricks/databricks-qwen35-122b-a10b": { + "cache_creation_input_token_cost": 2.2001e-07, + "cache_read_input_token_cost": 2.2001e-07, + "input_cost_per_token": 2.2001e-07, + "input_dbu_cost_per_token": 3.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 262144, + "max_output_tokens": 25000, + "max_tokens": 25000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 2.20003e-06, + "output_dbu_cost_per_token": 3.1429e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, + "databricks/databricks-qwen3-next-80b-a3b-instruct": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 1.5001e-07, + "input_cost_per_token": 1.5001e-07, + "input_dbu_cost_per_token": 2.143e-06, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "databricks/databricks-qwen3-embedding-0-6b": { + "cache_creation_input_token_cost": 2.002e-08, + "cache_read_input_token_cost": 2.002e-08, + "input_cost_per_token": 2.002e-08, + "input_dbu_cost_per_token": 2.86e-07, + "litellm_provider": "databricks", + "max_input_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" + }, "dataforseo/search": { "input_cost_per_query": 0.003, "litellm_provider": "dataforseo", @@ -31227,7 +31906,7 @@ "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -31259,7 +31938,7 @@ "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -31292,7 +31971,7 @@ "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31325,7 +32004,7 @@ "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31360,7 +32039,7 @@ "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31427,7 +32106,7 @@ "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -52723,7 +53402,7 @@ "cache_read_input_token_cost": 6e-08, "deprecation_date": "2026-07-23", "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -52756,7 +53435,7 @@ "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 616d58970cf..7304ca04eb5 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -5311,7 +5311,7 @@ "cache_read_input_token_cost": 4e-06, "deprecation_date": "2027-03-02", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5344,7 +5344,7 @@ "cache_read_input_token_cost": 4e-06, "deprecation_date": "2027-08-24", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5372,11 +5372,115 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "azure/gpt-realtime-2": { + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2026-08-31", + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 2.4e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-realtime-2.1": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "deprecation_date": "2027-06-25", + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image_token": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 2.4e-05, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, + "azure/gpt-realtime-2.1-mini": { + "cache_creation_input_audio_token_cost": 3e-07, + "cache_read_input_audio_token_cost": 3e-07, + "cache_read_input_token_cost": 6e-08, + "deprecation_date": "2027-06-25", + "input_cost_per_audio_token": 1e-05, + "input_cost_per_image_token": 8e-07, + "input_cost_per_token": 6e-07, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "realtime", + "output_cost_per_audio_token": 2e-05, + "output_cost_per_token": 2.4e-06, + "source": "https://learn.microsoft.com/en-us/azure/foundry/foundry-models/concepts/models-sold-directly-by-azure", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "azure/gpt-realtime-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -5408,7 +5512,7 @@ "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "azure", "max_input_tokens": 32000, @@ -16995,6 +17099,7 @@ "databricks/databricks-claude-3-7-sonnet": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, + "deprecation_date": "2026-04-12", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -17042,6 +17147,35 @@ "supports_vision": false, "thinking_always_on": true }, + "databricks/databricks-claude-fable-5-1": { + "cache_creation_input_token_cost": 1.250004e-05, + "cache_read_input_token_cost": 2.5004e-07, + "input_cost_per_token": 1.000006e-05, + "input_dbu_cost_per_token": 0.000142858, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.000002e-05, + "output_dbu_cost_per_token": 0.000714286, + "prompt_cache_min_tokens": 512, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supports_adaptive_thinking": true, + "supports_assistant_prefill": false, + "supports_forced_tool_use": false, + "supports_function_calling": true, + "supports_mid_conversation_system": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_sampling_params": false, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, "databricks/databricks-claude-haiku-4-5": { "cache_creation_input_token_cost": 1.24999e-06, "cache_read_input_token_cost": 1.0003e-07, @@ -17242,6 +17376,7 @@ "databricks/databricks-claude-sonnet-4": { "cache_creation_input_token_cost": 3.74997e-06, "cache_read_input_token_cost": 3.0002e-07, + "deprecation_date": "2026-10-09", "input_cost_per_token": 2.9999900000000002e-06, "input_dbu_cost_per_token": 4.2857e-05, "litellm_provider": "databricks", @@ -17254,13 +17389,13 @@ "mode": "chat", "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, + "prompt_cache_min_tokens": 1024, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_tool_choice": true, - "prompt_cache_min_tokens": 1024 + "supports_tool_choice": true }, "databricks/databricks-claude-sonnet-4-1": { "cache_creation_input_token_cost": 3.74997e-06, @@ -17417,6 +17552,7 @@ "databricks/databricks-gemini-2-5-flash": { "cache_creation_input_token_cost": 3.0002e-07, "cache_read_input_token_cost": 3.0002e-08, + "deprecation_date": "2026-10-02", "input_cost_per_token": 3.0001999999999996e-07, "input_dbu_cost_per_token": 4.285999999999999e-06, "litellm_provider": "databricks", @@ -17474,6 +17610,48 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "databricks/databricks-gemini-3-1-flash-image": { + "litellm_provider": "databricks", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, + "databricks/databricks-gemini-3-pro-image": { + "litellm_provider": "databricks", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_vision": true + }, "databricks/databricks-gemini-3-1-pro": { "cache_creation_input_token_cost": 2.49998e-06, "cache_read_input_token_cost": 2.4997e-07, @@ -17534,6 +17712,148 @@ "supports_prompt_caching": true, "supports_tool_choice": true }, + "databricks/databricks-gemini-3-8-flash": { + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-7-flash": { + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Databricks DBU rates not yet published for this model; endpoint metadata only." + }, + "mode": "chat", + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-6-flash": { + "cache_creation_input_token_cost": 1.87502e-06, + "cache_read_input_token_cost": 1.8753e-07, + "input_cost_per_token": 1.87502e-06, + "input_dbu_cost_per_token": 2.6786e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 9.37503e-06, + "output_dbu_cost_per_token": 0.000133929, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-5-flash": { + "cache_creation_input_token_cost": 1.87502e-06, + "cache_read_input_token_cost": 1.8753e-07, + "input_cost_per_token": 1.87502e-06, + "input_dbu_cost_per_token": 2.6786e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.124998e-05, + "output_dbu_cost_per_token": 0.000160714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gemini-3-5-flash-lite": { + "cache_creation_input_token_cost": 3.7499e-07, + "cache_read_input_token_cost": 3.752e-08, + "input_cost_per_token": 3.7499e-07, + "input_dbu_cost_per_token": 5.357e-06, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 3.12501e-06, + "output_dbu_cost_per_token": 4.4643e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, "cache_read_input_token_cost": 1.5001e-07, @@ -17579,16 +17899,53 @@ "supports_tool_choice": true, "supports_vision": false }, + "databricks/databricks-glm-5-3": { + "cache_creation_input_token_cost": 1.4e-06, + "cache_read_input_token_cost": 2.5998e-07, + "input_cost_per_token": 1.4e-06, + "input_dbu_cost_per_token": 2e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 4.39999e-06, + "output_dbu_cost_per_token": 6.2857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, "databricks/databricks-glm-5-3-flash": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 3.003e-08, + "input_cost_per_token": 1.5001e-07, + "input_dbu_cost_per_token": 2.143e-06, "litellm_provider": "databricks", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "metadata": { - "notes": "Databricks has not published pay-per-token DBU rates for this model yet (not on the foundation-model-serving pricing page as of 2026-08-27), so cost fields are omitted until rates are published." + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." }, "mode": "chat", - "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", + "output_cost_per_token": 5.0001e-07, + "output_dbu_cost_per_token": 7.143e-06, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supported_modalities": [ "text", "image" @@ -17600,7 +17957,8 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "thinking_always_on": true }, "databricks/databricks-gpt-5": { "cache_creation_input_token_cost": 1.24999e-06, @@ -17618,7 +17976,9 @@ "output_cost_per_token": 9.999990000000002e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-1": { "cache_creation_input_token_cost": 1.24999e-06, @@ -17636,11 +17996,14 @@ "output_cost_per_token": 9.999990000000002e-06, "output_dbu_cost_per_token": 0.000142857, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-1-codex-max": { "cache_creation_input_token_cost": 1.24999e-06, "cache_read_input_token_cost": 1.2502e-07, + "deprecation_date": "2026-07-16", "input_cost_per_token": 1.24999e-06, "input_dbu_cost_per_token": 1.7857e-05, "litellm_provider": "databricks", @@ -17659,6 +18022,7 @@ "databricks/databricks-gpt-5-1-codex-mini": { "cache_creation_input_token_cost": 2.4997e-07, "cache_read_input_token_cost": 2.499e-08, + "deprecation_date": "2026-07-16", "input_cost_per_token": 2.4997e-07, "input_dbu_cost_per_token": 3.571e-06, "litellm_provider": "databricks", @@ -17690,11 +18054,14 @@ "output_cost_per_token": 1.4e-05, "output_dbu_cost_per_token": 0.0002, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-2-codex": { "cache_creation_input_token_cost": 1.75e-06, "cache_read_input_token_cost": 1.75e-07, + "deprecation_date": "2026-07-16", "input_cost_per_token": 1.75e-06, "input_dbu_cost_per_token": 2.5e-05, "litellm_provider": "databricks", @@ -17726,7 +18093,9 @@ "output_cost_per_token": 1.4e-05, "output_dbu_cost_per_token": 0.0002, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-4": { "cache_creation_input_token_cost": 2.49998e-06, @@ -17734,7 +18103,7 @@ "input_cost_per_token": 2.49998e-06, "input_dbu_cost_per_token": 3.5714e-05, "litellm_provider": "databricks", - "max_input_tokens": 272000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "metadata": { @@ -17744,7 +18113,18 @@ "output_cost_per_token": 1.5000020000000002e-05, "output_dbu_cost_per_token": 0.000214286, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-4-mini": { "cache_creation_input_token_cost": 7.4998e-07, @@ -17762,7 +18142,18 @@ "output_cost_per_token": 4.50002e-06, "output_dbu_cost_per_token": 6.4286e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-4-nano": { "cache_creation_input_token_cost": 1.9999e-07, @@ -17780,7 +18171,163 @@ "output_cost_per_token": 1.24999e-06, "output_dbu_cost_per_token": 1.7857e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-sol": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 3.9998e-07, + "input_cost_per_token": 4.00001e-06, + "input_dbu_cost_per_token": 5.7143e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields. Rates reflect OpenAI's promotional pricing in effect through November 21, 2026; afterwards input, cache and Batch rates are 25% higher and output rates 50% higher." + }, + "mode": "chat", + "output_cost_per_token": 1.999998e-05, + "output_dbu_cost_per_token": 0.000285714, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-terra": { + "cache_creation_input_token_cost": 3.12501e-06, + "cache_read_input_token_cost": 2.4997e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.500002e-05, + "output_dbu_cost_per_token": 0.000214286, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-6-luna": { + "cache_creation_input_token_cost": 1.24999e-06, + "cache_read_input_token_cost": 1.0003e-07, + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 5.99998e-06, + "output_dbu_cost_per_token": 8.5714e-05, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-5": { + "cache_creation_input_token_cost": 5.00003e-06, + "cache_read_input_token_cost": 5.0001e-07, + "input_cost_per_token": 5.00003e-06, + "input_dbu_cost_per_token": 7.1429e-05, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 2.999997e-05, + "output_dbu_cost_per_token": 0.000428571, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "databricks/databricks-gpt-5-5-pro": { + "cache_creation_input_token_cost": 2.999997e-05, + "cache_read_input_token_cost": 2.999997e-05, + "input_cost_per_token": 2.999997e-05, + "input_dbu_cost_per_token": 0.000428571, + "litellm_provider": "databricks", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "responses", + "output_cost_per_token": 0.00018000003, + "output_dbu_cost_per_token": 0.002571429, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true }, "databricks/databricks-gpt-5-mini": { "cache_creation_input_token_cost": 2.4997e-07, @@ -17798,7 +18345,9 @@ "output_cost_per_token": 1.9999700000000004e-06, "output_dbu_cost_per_token": 2.8571e-05, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-5-nano": { "cache_creation_input_token_cost": 4.998e-08, @@ -17816,7 +18365,9 @@ "output_cost_per_token": 3.9998000000000007e-07, "output_dbu_cost_per_token": 5.714000000000001e-06, "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", - "supports_prompt_caching": true + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_tool_choice": true }, "databricks/databricks-gpt-oss-120b": { "cache_creation_input_token_cost": 1.5001e-07, @@ -17852,6 +18403,32 @@ "output_dbu_cost_per_token": 4.285999999999999e-06, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-grok-4-6": { + "cache_creation_input_token_cost": 2.49998e-06, + "cache_read_input_token_cost": 6.2503e-07, + "input_cost_per_token": 2.49998e-06, + "input_dbu_cost_per_token": 3.5714e-05, + "litellm_provider": "databricks", + "max_input_tokens": 500000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 7.50001e-06, + "output_dbu_cost_per_token": 0.000107143, + "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false + }, "databricks/databricks-gte-large-en": { "cache_creation_input_token_cost": 1.2999e-07, "cache_read_input_token_cost": 1.2999e-07, @@ -17869,6 +18446,34 @@ "output_vector_size": 1024, "source": "https://www.databricks.com/product/pricing/foundation-model-serving" }, + "databricks/databricks-inkling": { + "cache_creation_input_token_cost": 1.00002e-06, + "cache_read_input_token_cost": 1.7003e-07, + "input_cost_per_token": 1.00002e-06, + "input_dbu_cost_per_token": 1.4286e-05, + "litellm_provider": "databricks", + "max_input_tokens": 1000000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 4.04999e-06, + "output_dbu_cost_per_token": 5.7857e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "thinking_always_on": true + }, "databricks/databricks-kimi-k3": { "cache_creation_input_token_cost": 2.99999e-06, "cache_read_input_token_cost": 3.0002e-07, @@ -17901,6 +18506,7 @@ "databricks/databricks-llama-2-70b-chat": { "cache_creation_input_token_cost": 5.0001e-07, "cache_read_input_token_cost": 5.0001e-07, + "deprecation_date": "2024-10-30", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -17937,6 +18543,7 @@ "databricks/databricks-meta-llama-3-1-405b-instruct": { "cache_creation_input_token_cost": 5.00003e-06, "cache_read_input_token_cost": 5.00003e-06, + "deprecation_date": "2026-02-15", "input_cost_per_token": 5.00003e-06, "input_dbu_cost_per_token": 7.1429e-05, "litellm_provider": "databricks", @@ -17990,6 +18597,7 @@ "databricks/databricks-meta-llama-3-70b-instruct": { "cache_creation_input_token_cost": 1.00002e-06, "cache_read_input_token_cost": 1.00002e-06, + "deprecation_date": "2024-07-23", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -18008,6 +18616,7 @@ "databricks/databricks-mixtral-8x7b-instruct": { "cache_creation_input_token_cost": 5.0001e-07, "cache_read_input_token_cost": 5.0001e-07, + "deprecation_date": "2025-04-30", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -18026,6 +18635,7 @@ "databricks/databricks-mpt-30b-instruct": { "cache_creation_input_token_cost": 1.00002e-06, "cache_read_input_token_cost": 1.00002e-06, + "deprecation_date": "2024-08-30", "input_cost_per_token": 1.00002e-06, "input_dbu_cost_per_token": 1.4286e-05, "litellm_provider": "databricks", @@ -18044,6 +18654,7 @@ "databricks/databricks-mpt-7b-instruct": { "cache_creation_input_token_cost": 5.0001e-07, "cache_read_input_token_cost": 5.0001e-07, + "deprecation_date": "2024-08-30", "input_cost_per_token": 5.0001e-07, "input_dbu_cost_per_token": 7.143e-06, "litellm_provider": "databricks", @@ -18059,6 +18670,74 @@ "source": "https://www.databricks.com/product/pricing/foundation-model-serving", "supports_tool_choice": true }, + "databricks/databricks-qwen35-122b-a10b": { + "cache_creation_input_token_cost": 2.2001e-07, + "cache_read_input_token_cost": 2.2001e-07, + "input_cost_per_token": 2.2001e-07, + "input_dbu_cost_per_token": 3.143e-06, + "litellm_provider": "databricks", + "max_input_tokens": 262144, + "max_output_tokens": 25000, + "max_tokens": 25000, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 2.20003e-06, + "output_dbu_cost_per_token": 3.1429e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": false, + "thinking_always_on": true + }, + "databricks/databricks-qwen3-next-80b-a3b-instruct": { + "cache_creation_input_token_cost": 1.5001e-07, + "cache_read_input_token_cost": 1.5001e-07, + "input_cost_per_token": 1.5001e-07, + "input_dbu_cost_per_token": 2.143e-06, + "litellm_provider": "databricks", + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "chat", + "output_cost_per_token": 1.20001e-06, + "output_dbu_cost_per_token": 1.7143e-05, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving", + "supported_modalities": [ + "text" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "databricks/databricks-qwen3-embedding-0-6b": { + "cache_creation_input_token_cost": 2.002e-08, + "cache_read_input_token_cost": 2.002e-08, + "input_cost_per_token": 2.002e-08, + "input_dbu_cost_per_token": 2.86e-07, + "litellm_provider": "databricks", + "max_input_tokens": 32768, + "max_tokens": 32768, + "metadata": { + "notes": "Costs per token are the published Global DBU rates times $0.070 per DBU. The '*_dbu_cost_per_token' fields are provided for reference; cost calculation reads the dollar '*_cost_per_token' fields." + }, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_dbu_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://www.databricks.com/product/pricing/foundation-model-serving" + }, "dataforseo/search": { "input_cost_per_query": 0.003, "litellm_provider": "dataforseo", @@ -31227,7 +31906,7 @@ "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -31259,7 +31938,7 @@ "cache_creation_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -31292,7 +31971,7 @@ "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31325,7 +32004,7 @@ "cache_read_input_audio_token_cost": 4e-07, "cache_read_input_token_cost": 4e-07, "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31360,7 +32039,7 @@ "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -31427,7 +32106,7 @@ "cache_read_input_token_cost": 4e-07, "deprecation_date": "2027-01-20", "input_cost_per_audio_token": 3.2e-05, - "input_cost_per_image": 5e-06, + "input_cost_per_image_token": 5e-06, "input_cost_per_token": 4e-06, "litellm_provider": "openai", "max_input_tokens": 32000, @@ -52723,7 +53402,7 @@ "cache_read_input_token_cost": 6e-08, "deprecation_date": "2026-07-23", "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, @@ -52756,7 +53435,7 @@ "cache_read_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, "input_cost_per_audio_token": 1e-05, - "input_cost_per_image": 8e-07, + "input_cost_per_image_token": 8e-07, "input_cost_per_token": 6e-07, "litellm_provider": "openai", "max_input_tokens": 128000, diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 311ba7aebc0..0f8084643ea 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -4630,6 +4630,28 @@ def test_generic_cost_per_token_grok_46_long_context(_local_model_cost_map): assert completion_cost == pytest.approx(1_000 * 1.2e-05) +@pytest.mark.parametrize( + ("model", "provider", "image_token_rate"), + [ + ("gpt-realtime-2.1", "openai", 5e-06), + ("gpt-realtime-2.1-mini", "openai", 8e-07), + ("azure/gpt-realtime-2.1", "azure", 5e-06), + ("azure/gpt-realtime-2.1-mini", "azure", 8e-07), + ], +) +def test_realtime_image_tokens_priced_per_token(model, provider, image_token_rate, _local_model_cost_map): + """Realtime image input is billed per 1M image tokens, not per image.""" + usage = Usage( + prompt_tokens=1_100, + completion_tokens=0, + total_tokens=1_100, + prompt_tokens_details=PromptTokensDetailsWrapper(text_tokens=100, image_tokens=1_000), + ) + prompt_cost, _ = generic_cost_per_token(model=model, usage=usage, custom_llm_provider=provider) + text_rate = litellm.model_cost[model]["input_cost_per_token"] + assert prompt_cost == pytest.approx(100 * text_rate + 1_000 * image_token_rate) + + @pytest.mark.parametrize( ("response_quality", "requested_quality", "expected_cost"), [ diff --git a/tests/test_litellm/llms/databricks/test_databricks_cost_calculator.py b/tests/test_litellm/llms/databricks/test_databricks_cost_calculator.py index e72642f7a04..0b251be5408 100644 --- a/tests/test_litellm/llms/databricks/test_databricks_cost_calculator.py +++ b/tests/test_litellm/llms/databricks/test_databricks_cost_calculator.py @@ -18,6 +18,10 @@ NEW_MODELS: Final = ( "databricks/databricks-claude-opus-5", "databricks/databricks-claude-sonnet-5", "databricks/databricks-claude-fable-5", + "databricks/databricks-claude-fable-5-1", + "databricks/databricks-gpt-5-6-sol", + "databricks/databricks-gpt-5-6-terra", + "databricks/databricks-gpt-5-6-luna", ) DOLLARS_PER_DBU: Final = Decimal("0.070") @@ -28,6 +32,7 @@ PRICE_FIELDS: Final = ( "cache_read_input_token_cost", ) PUBLISHED_DBU_PER_MILLION: Final = { + "databricks/databricks-claude-fable-5-1": ("142.858", "714.286", "178.572", "3.572"), "databricks/databricks-claude-fable-5": ("142.858", "714.286", "178.572", "14.286"), "databricks/databricks-claude-opus-5": ("71.429", "357.143", "89.286", "7.143"), "databricks/databricks-claude-opus-4-8": ("71.429", "357.143", "89.286", "7.143"), @@ -52,9 +57,17 @@ PUBLISHED_DBU_PER_MILLION: Final = { "databricks/databricks-gpt-5-2": ("25.000", "200.000", "25.000", "2.500"), "databricks/databricks-gpt-5-2-codex": ("25.000", "200.000", "25.000", "2.500"), "databricks/databricks-gpt-5-3-codex": ("25.000", "200.000", "25.000", "2.500"), + "databricks/databricks-gpt-5-6-sol": ("57.143", "285.714", "71.429", "5.714"), + "databricks/databricks-gpt-5-6-terra": ("35.714", "214.286", "44.643", "3.571"), + "databricks/databricks-gpt-5-6-luna": ("14.286", "85.714", "17.857", "1.429"), + "databricks/databricks-gpt-5-5": ("71.429", "428.571", "71.429", "7.143"), + "databricks/databricks-gpt-5-5-pro": ("428.571", "2571.429", "428.571", "428.571"), "databricks/databricks-gpt-5-4": ("35.714", "214.286", "35.714", "3.571"), "databricks/databricks-gpt-5-4-mini": ("10.714", "64.286", "10.714", "1.071"), "databricks/databricks-gpt-5-4-nano": ("2.857", "17.857", "2.857", "0.286"), + "databricks/databricks-gemini-3-6-flash": ("26.786", "133.929", "26.786", "2.679"), + "databricks/databricks-gemini-3-5-flash": ("26.786", "160.714", "26.786", "2.679"), + "databricks/databricks-gemini-3-5-flash-lite": ("5.357", "44.643", "5.357", "0.536"), "databricks/databricks-gemini-3-1-pro": ("35.714", "214.286", "35.714", "3.571"), "databricks/databricks-gemini-3-pro": ("35.714", "214.286", "35.714", "3.571"), "databricks/databricks-gemini-3-flash": ("8.929", "53.571", "8.929", "0.893"), @@ -65,6 +78,13 @@ PUBLISHED_DBU_PER_MILLION: Final = { "databricks/databricks-deepseek-v4-flash-0731": ("2.000", "4.000", "2.000", "0.400"), "databricks/databricks-deepseek-v4-pro-0813": ("18.857", "56.571", "18.857", "1.886"), "databricks/databricks-glm-5-2": ("20.000", "62.857", "20.000", "3.714"), + "databricks/databricks-glm-5-3": ("20.000", "62.857", "20.000", "3.714"), + "databricks/databricks-glm-5-3-flash": ("2.143", "7.143", "2.143", "0.429"), + "databricks/databricks-inkling": ("14.286", "57.857", "14.286", "2.429"), + "databricks/databricks-grok-4-6": ("35.714", "107.143", "35.714", "8.929"), + "databricks/databricks-qwen35-122b-a10b": ("3.143", "31.429", "3.143", "3.143"), + "databricks/databricks-qwen3-next-80b-a3b-instruct": ("2.143", "17.143", "2.143", "2.143"), + "databricks/databricks-qwen3-embedding-0-6b": ("0.286", "0", "0.286", "0.286"), } PROMOTIONAL_DISCOUNT: Final = 0.80 PROMOTION_EXPIRES: Final = "2027-01-31" @@ -73,6 +93,10 @@ ENTRIES_STORING_PROMOTIONAL_RATE: Final = ( "databricks/databricks-gemini-2-5-flash", ) ENTRIES_STORING_LIST_RATE_DESPITE_PROMOTION: Final = ( + "databricks/databricks-gemini-3-6-flash", + "databricks/databricks-gemini-3-5-flash", + "databricks/databricks-gemini-3-5-flash-lite", + "databricks/databricks-grok-4-6", "databricks/databricks-gemini-3-1-pro", "databricks/databricks-gemini-3-pro", "databricks/databricks-gemini-3-flash",