diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 3abf80c74b7..b1c38d0350a 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -352,6 +352,17 @@ "supports_function_calling": true, "supports_pdf_input": true }, + "writer.palmyra-vision-7b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-vision-7b.html", + "supports_vision": true + }, "amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, @@ -366,7 +377,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.5e-08 }, "amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, @@ -549,7 +561,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 8.75e-09 }, "amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, @@ -565,7 +578,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 2e-07 }, "amazon.nova-sonic-v1:0": { "deprecation_date": "2026-09-14", @@ -3796,6 +3810,53 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure_ai/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure_ai/gpt-5.4": { "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, @@ -5311,6 +5372,7 @@ "supports_vision": true }, "azure/gpt-4o": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -7510,6 +7572,70 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-sol-2026-07-09": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_flex": 2e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_flex": 2e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "output_cost_per_token_flex": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, @@ -7574,6 +7700,70 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-terra-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_read_input_token_cost_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_flex": 1e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_flex": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, + "output_cost_per_token_priority": 2.4e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, + "output_cost_per_token_flex": 6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, @@ -7638,6 +7828,70 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-luna-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, + "cache_creation_input_token_cost_priority": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, + "cache_read_input_token_cost_priority": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_flex": 1e-08, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, + "input_cost_per_token_priority": 4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_flex": 1e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, + "output_cost_per_token_priority": 2.4e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "output_cost_per_token_flex": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, @@ -7686,6 +7940,54 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/gpt-6-astra-2026-09-03": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, "deprecation_date": "2026-12-02", @@ -8502,6 +8804,63 @@ "output_cost_per_token_batches": 1.5e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_priority": 1.25e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token_flex": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_batches": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_priority": 7.5e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, @@ -8550,6 +8909,57 @@ "output_cost_per_token_batches": 1.65e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/us/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, @@ -8598,6 +9008,57 @@ "output_cost_per_token_batches": 1.65e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/eu/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, @@ -9055,6 +9516,36 @@ "supports_vision": true, "supports_pdf_input": true }, + "azure/gpt-image-2.5-flare": { + "deprecation_date": "2027-09-09", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "azure/gpt-image-2.5-sunburst": { + "deprecation_date": "2027-09-09", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, "azure/gpt-image-2-2026-04-21": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", @@ -11371,6 +11862,7 @@ "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -11389,6 +11881,7 @@ "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -13904,7 +14397,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -13939,7 +14432,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -13960,7 +14453,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.anthropic.com/en/docs/about-claude/pricing" }, "claude-sonnet-5": { "deprecation_date": "2027-06-30", @@ -15089,6 +15583,21 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "command-a-plus-05-2026": { + "input_cost_per_token": 0.0, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.cohere.com/docs/command-a-plus", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "command-light": { "input_cost_per_token": 3e-07, "litellm_provider": "cohere_chat", @@ -26884,13 +27393,71 @@ "supports_image_size": false }, "gemini/gemini-flash-latest": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" + }, + "gemini/gemini-flash-lite-latest": { "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -26924,58 +27491,23 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 - }, - "gemini/gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini/gemini-2.5-flash-lite-preview-06-17": { "deprecation_date": "2025-11-18", @@ -32153,7 +32685,7 @@ "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -32192,7 +32724,7 @@ "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -34977,6 +35509,7 @@ "supports_tool_choice": true }, "inception/mercury-2.5": { + "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "inception", "max_input_tokens": 260000, @@ -34986,6 +35519,7 @@ "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true @@ -36525,6 +37059,57 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/zai-glm-5-3": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-5": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-latest": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "mistral/glm-5-2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -38151,6 +38736,15 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" }, + "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { + "input_cost_per_token": 1.32e-06, + "litellm_provider": "nebius", + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/MiniMaxAI/MiniMax-M2.5": { "max_tokens": 196608, "max_input_tokens": 196608, @@ -38417,6 +39011,17 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" }, + "nebius/zai-org/GLM-5.3": { + "input_cost_per_token": 1.4e-06, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/zai-org/GLM-5.3-Flash": { "max_tokens": 1024000, "max_input_tokens": 1024000, @@ -40250,15 +40855,16 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 3.2e-07, + "input_cost_per_token": 2.574e-07, "litellm_provider": "openrouter", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 8.9e-07, + "output_cost_per_token": 1.0287e-06, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/deepseek/deepseek-chat-v3-0324": { "input_cost_per_token": 2.5e-07, @@ -40351,21 +40957,21 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 8.59908e-07, + "input_cost_per_token": 1.6e-06, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.719816e-06, + "output_cost_per_token": 3.2e-06, "source": "https://openrouter.ai/deepseek/deepseek-v4-pro", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "cache_read_input_token_cost": 7.1659e-08 + "cache_read_input_token_cost": 1.35e-07 }, "openrouter/deepseek/deepseek-v4.1-flash": { "input_cost_per_token": 1.5e-07, @@ -40660,12 +41266,13 @@ "supports_vision": true }, "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 6e-08, + "input_cost_per_token": 8e-08, "litellm_provider": "openrouter", "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-08, - "supports_tool_choice": true + "output_cost_per_token": 1.1e-07, + "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/mancer/weaver": { "input_cost_per_token": 4e-07, @@ -40801,14 +41408,15 @@ "max_output_tokens": 131072 }, "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 7.5e-08, + "input_cost_per_token": 9.375e-08, "litellm_provider": "openrouter", "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-07, + "output_cost_per_token": 2.5e-07, "supports_tool_choice": true, "max_input_tokens": 128000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/mistralai/mixtral-8x22b-instruct": { "input_cost_per_token": 2e-06, @@ -41329,13 +41937,13 @@ "supports_tool_choice": true }, "openrouter/qwen/qwen3-235b-a22b-2507": { - "input_cost_per_token": 2.2e-07, + "input_cost_per_token": 8.75e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 8.8e-07, + "output_cost_per_token": 3.5e-07, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", "supports_function_calling": true, "supports_tool_choice": true @@ -41368,13 +41976,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-35b-a3b": { - "input_cost_per_token": 3.125e-07, + "input_cost_per_token": 1.625e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.25e-06, + "output_cost_per_token": 1.3e-06, "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", "supports_function_calling": true, "supports_reasoning": true, @@ -44390,7 +44998,7 @@ "deprecation_date": "2026-06-04", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", - "max_input_tokens": 256000, + "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models", @@ -44460,7 +45068,7 @@ "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 16384 }, "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { @@ -44643,7 +45251,7 @@ "deprecation_date": "2026-04-02", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.1e-06, "source": "https://api.together.ai/v1/models", @@ -44870,6 +45478,20 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.xyz/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "together_ai/deepseek-ai/DeepSeek-V4-Pro": { "deprecation_date": "2026-08-27", "cache_read_input_token_cost": 2e-07, @@ -45172,7 +45794,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.5e-08 }, "us.amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, @@ -45186,7 +45809,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 8.75e-09 }, "us.amazon.nova-premier-v1:0": { "deprecation_date": "2026-09-14", @@ -45199,9 +45823,10 @@ "output_cost_per_token": 1.25e-05, "supports_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 6.25e-07 }, "us.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, @@ -45217,7 +45842,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 2e-07 }, "us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, @@ -49453,6 +50079,7 @@ "output_cost_per_token": 5e-07, "source": "https://docs.x.ai/developers/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -49469,6 +50096,7 @@ "output_cost_per_token": 5e-07, "source": "https://docs.x.ai/developers/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -49489,6 +50117,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -49508,6 +50137,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -49528,6 +50158,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -49547,6 +50178,7 @@ "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -56015,6 +56647,73 @@ "input_cost_per_second": 8.33333333333e-05, "supports_response_schema": false }, + "gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true + }, + "gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true, + "supports_reasoning": true + }, "gemini/gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, @@ -56180,18 +56879,17 @@ "supports_web_search": false }, "gemini-flash-latest": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 2.5e-06, - "output_cost_per_token": 2.5e-06, + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -56220,25 +56918,37 @@ "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -56267,29 +56977,42 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -56313,29 +57036,45 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -56359,11 +57098,26 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-exp-1206": { "cache_read_input_token_cost": 3e-08, @@ -57263,6 +58017,38 @@ } ] }, + "volcengine/doubao-seed-2-1-pro-260628": { + "cache_read_input_token_cost": 1.725e-07, + "input_cost_per_token": 8.625e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4.3125e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-turbo-260628": { + "cache_read_input_token_cost": 8.625e-08, + "input_cost_per_token": 4.3125e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.15625e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, "volcengine/doubao-seed-2-0-lite-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, @@ -58989,7 +59775,8 @@ "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_response_schema": true }, "fireworks_ai/accounts/fireworks/models/kimi-k3": { "cache_read_input_token_cost": 3e-07, @@ -59065,7 +59852,8 @@ "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_response_schema": true }, "fireworks_ai/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, @@ -62056,6 +62844,36 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_priority": 3.75e-08, @@ -64225,9 +65043,9 @@ "supports_prompt_caching": true }, "openrouter/z-ai/glm-5.3-flash": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 5e-07, - "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 1.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 131072, @@ -64277,9 +65095,9 @@ "supports_prompt_caching": true }, "openrouter/qwen/qwen3.8-27b": { - "input_cost_per_token": 4.2e-07, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 8.5e-08, + "input_cost_per_token": 2.14e-07, + "output_cost_per_token": 2.55e-06, + "cache_read_input_token_cost": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 131072, @@ -64362,9 +65180,9 @@ "supports_prompt_caching": true }, "openrouter/deepseek/deepseek-v4-flash-0731": { - "input_cost_per_token": 6.5e-08, - "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.2e-07, + "cache_read_input_token_cost": 1.2e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, @@ -64432,9 +65250,9 @@ "supports_vision": false }, "openrouter/moonshotai/kimi-k3": { - "input_cost_per_token": 2.1e-06, - "output_cost_per_token": 1.053e-05, - "cache_read_input_token_cost": 2.35e-07, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 943718, @@ -64531,9 +65349,9 @@ "supports_prompt_caching": true }, "openrouter/z-ai/glm-5.2": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 131072, @@ -64564,9 +65382,9 @@ "supports_vision": false }, "openrouter/moonshotai/kimi-k2.7-code": { - "input_cost_per_token": 7.1e-07, - "output_cost_per_token": 3.5e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 7.062e-07, + "output_cost_per_token": 3.21e-06, + "cache_read_input_token_cost": 1.8e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 235929, @@ -64868,8 +65686,8 @@ "supports_prompt_caching": true }, "openrouter/google/gemma-4-26b-a4b-it": { - "input_cost_per_token": 4.2e-08, - "output_cost_per_token": 2.2e-07, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 16384, @@ -65416,8 +66234,8 @@ "supports_vision": true }, "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 5.2e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 16384, @@ -65677,8 +66495,8 @@ "supports_vision": false }, "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 4.815e-08, + "output_cost_per_token": 1.9305e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 32000, @@ -65737,7 +66555,7 @@ "supports_vision": false }, "openrouter/minimax/minimax-m1": { - "input_cost_per_token": 5.5e-07, + "input_cost_per_token": 4e-07, "output_cost_per_token": 2.2e-06, "litellm_provider": "openrouter", "max_input_tokens": 1000000, @@ -65876,8 +66694,8 @@ "supports_vision": false }, "openrouter/qwen/qwen3-14b": { - "input_cost_per_token": 2.275e-07, - "output_cost_per_token": 9.1e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 2.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 16384, @@ -65939,8 +66757,8 @@ "supports_prompt_caching": true }, "openrouter/meta-llama/llama-4-maverick": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6.96e-07, + "input_cost_per_token": 1.875e-07, + "output_cost_per_token": 6.525e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 115200, @@ -66361,14 +67179,6 @@ "supports_response_schema": true, "supports_vision": false }, - "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { - "cache_read_input_token_cost": 3.9e-07, - "input_cost_per_token": 2.1e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://api.fireworks.ai/v1/serverless/models" - }, "together_ai/arcee-ai/trinity-mini": { "input_cost_per_token": 4.5e-08, "litellm_provider": "together_ai", @@ -66408,14 +67218,6 @@ "output_cost_per_token": 1.6e-06, "source": "https://api.together.ai/v1/models" }, - "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" - }, "vertex_ai/gemini-2.5-flash-native-audio": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 3abf80c74b7..b1c38d0350a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -352,6 +352,17 @@ "supports_function_calling": true, "supports_pdf_input": true }, + "writer.palmyra-vision-7b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-vision-7b.html", + "supports_vision": true + }, "amazon.nova-lite-v1:0": { "cache_read_input_token_cost": 1.5e-08, "input_cost_per_token": 6e-08, @@ -366,7 +377,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.5e-08 }, "amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, @@ -549,7 +561,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 8.75e-09 }, "amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, @@ -565,7 +578,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 2e-07 }, "amazon.nova-sonic-v1:0": { "deprecation_date": "2026-09-14", @@ -3796,6 +3810,53 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure_ai/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure_ai/gpt-5.4": { "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, @@ -5311,6 +5372,7 @@ "supports_vision": true }, "azure/gpt-4o": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -7510,6 +7572,70 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-sol-2026-07-09": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_flex": 2e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_flex": 2e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "output_cost_per_token_flex": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, @@ -7574,6 +7700,70 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-terra-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_read_input_token_cost_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_flex": 1e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_flex": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, + "output_cost_per_token_priority": 2.4e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, + "output_cost_per_token_flex": 6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, @@ -7638,6 +7828,70 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-luna-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, + "cache_creation_input_token_cost_priority": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, + "cache_read_input_token_cost_priority": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_flex": 1e-08, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, + "input_cost_per_token_priority": 4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_flex": 1e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, + "output_cost_per_token_priority": 2.4e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "output_cost_per_token_flex": 6e-07, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, @@ -7686,6 +7940,54 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/gpt-6-astra-2026-09-03": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, "deprecation_date": "2026-12-02", @@ -8502,6 +8804,63 @@ "output_cost_per_token_batches": 1.5e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, + "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_priority": 1.25e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token_flex": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_batches": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_priority": 7.5e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, @@ -8550,6 +8909,57 @@ "output_cost_per_token_batches": 1.65e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/us/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, @@ -8598,6 +9008,57 @@ "output_cost_per_token_batches": 1.65e-05, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, + "azure/eu/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.375e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, @@ -9055,6 +9516,36 @@ "supports_vision": true, "supports_pdf_input": true }, + "azure/gpt-image-2.5-flare": { + "deprecation_date": "2027-09-09", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "azure/gpt-image-2.5-sunburst": { + "deprecation_date": "2027-09-09", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, "azure/gpt-image-2-2026-04-21": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", @@ -11371,6 +11862,7 @@ "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -11389,6 +11881,7 @@ "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -13904,7 +14397,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -13939,7 +14432,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -13960,7 +14453,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.anthropic.com/en/docs/about-claude/pricing" }, "claude-sonnet-5": { "deprecation_date": "2027-06-30", @@ -15089,6 +15583,21 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "command-a-plus-05-2026": { + "input_cost_per_token": 0.0, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.cohere.com/docs/command-a-plus", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "command-light": { "input_cost_per_token": 3e-07, "litellm_provider": "cohere_chat", @@ -26884,13 +27393,71 @@ "supports_image_size": false }, "gemini/gemini-flash-latest": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" + }, + "gemini/gemini-flash-lite-latest": { "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -26924,58 +27491,23 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 - }, - "gemini/gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini/gemini-2.5-flash-lite-preview-06-17": { "deprecation_date": "2025-11-18", @@ -32153,7 +32685,7 @@ "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -32192,7 +32724,7 @@ "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -34977,6 +35509,7 @@ "supports_tool_choice": true }, "inception/mercury-2.5": { + "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "inception", "max_input_tokens": 260000, @@ -34986,6 +35519,7 @@ "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true @@ -36525,6 +37059,57 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/zai-glm-5-3": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-5": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-latest": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "mistral/glm-5-2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -38151,6 +38736,15 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" }, + "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { + "input_cost_per_token": 1.32e-06, + "litellm_provider": "nebius", + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/MiniMaxAI/MiniMax-M2.5": { "max_tokens": 196608, "max_input_tokens": 196608, @@ -38417,6 +39011,17 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" }, + "nebius/zai-org/GLM-5.3": { + "input_cost_per_token": 1.4e-06, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/zai-org/GLM-5.3-Flash": { "max_tokens": 1024000, "max_input_tokens": 1024000, @@ -40250,15 +40855,16 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 3.2e-07, + "input_cost_per_token": 2.574e-07, "litellm_provider": "openrouter", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 8.9e-07, + "output_cost_per_token": 1.0287e-06, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/deepseek/deepseek-chat-v3-0324": { "input_cost_per_token": 2.5e-07, @@ -40351,21 +40957,21 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 8.59908e-07, + "input_cost_per_token": 1.6e-06, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.719816e-06, + "output_cost_per_token": 3.2e-06, "source": "https://openrouter.ai/deepseek/deepseek-v4-pro", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "cache_read_input_token_cost": 7.1659e-08 + "cache_read_input_token_cost": 1.35e-07 }, "openrouter/deepseek/deepseek-v4.1-flash": { "input_cost_per_token": 1.5e-07, @@ -40660,12 +41266,13 @@ "supports_vision": true }, "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 6e-08, + "input_cost_per_token": 8e-08, "litellm_provider": "openrouter", "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-08, - "supports_tool_choice": true + "output_cost_per_token": 1.1e-07, + "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/mancer/weaver": { "input_cost_per_token": 4e-07, @@ -40801,14 +41408,15 @@ "max_output_tokens": 131072 }, "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 7.5e-08, + "input_cost_per_token": 9.375e-08, "litellm_provider": "openrouter", "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-07, + "output_cost_per_token": 2.5e-07, "supports_tool_choice": true, "max_input_tokens": 128000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/mistralai/mixtral-8x22b-instruct": { "input_cost_per_token": 2e-06, @@ -41329,13 +41937,13 @@ "supports_tool_choice": true }, "openrouter/qwen/qwen3-235b-a22b-2507": { - "input_cost_per_token": 2.2e-07, + "input_cost_per_token": 8.75e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 8.8e-07, + "output_cost_per_token": 3.5e-07, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", "supports_function_calling": true, "supports_tool_choice": true @@ -41368,13 +41976,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-35b-a3b": { - "input_cost_per_token": 3.125e-07, + "input_cost_per_token": 1.625e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.25e-06, + "output_cost_per_token": 1.3e-06, "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", "supports_function_calling": true, "supports_reasoning": true, @@ -44390,7 +44998,7 @@ "deprecation_date": "2026-06-04", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", - "max_input_tokens": 256000, + "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models", @@ -44460,7 +45068,7 @@ "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 16384 }, "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { @@ -44643,7 +45251,7 @@ "deprecation_date": "2026-04-02", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.1e-06, "source": "https://api.together.ai/v1/models", @@ -44870,6 +45478,20 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://api.together.xyz/v1/models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "together_ai/deepseek-ai/DeepSeek-V4-Pro": { "deprecation_date": "2026-08-27", "cache_read_input_token_cost": 2e-07, @@ -45172,7 +45794,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.5e-08 }, "us.amazon.nova-micro-v1:0": { "cache_read_input_token_cost": 8.75e-09, @@ -45186,7 +45809,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 8.75e-09 }, "us.amazon.nova-premier-v1:0": { "deprecation_date": "2026-09-14", @@ -45199,9 +45823,10 @@ "output_cost_per_token": 1.25e-05, "supports_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 6.25e-07 }, "us.amazon.nova-pro-v1:0": { "cache_read_input_token_cost": 2e-07, @@ -45217,7 +45842,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 2e-07 }, "us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, @@ -49453,6 +50079,7 @@ "output_cost_per_token": 5e-07, "source": "https://docs.x.ai/developers/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -49469,6 +50096,7 @@ "output_cost_per_token": 5e-07, "source": "https://docs.x.ai/developers/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -49489,6 +50117,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -49508,6 +50137,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -49528,6 +50158,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -49547,6 +50178,7 @@ "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -56015,6 +56647,73 @@ "input_cost_per_second": 8.33333333333e-05, "supports_response_schema": false }, + "gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true + }, + "gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true, + "supports_reasoning": true + }, "gemini/gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, @@ -56180,18 +56879,17 @@ "supports_web_search": false }, "gemini-flash-latest": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 2.5e-06, - "output_cost_per_token": 2.5e-06, + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -56220,25 +56918,37 @@ "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -56267,29 +56977,42 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -56313,29 +57036,45 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -56359,11 +57098,26 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-exp-1206": { "cache_read_input_token_cost": 3e-08, @@ -57263,6 +58017,38 @@ } ] }, + "volcengine/doubao-seed-2-1-pro-260628": { + "cache_read_input_token_cost": 1.725e-07, + "input_cost_per_token": 8.625e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4.3125e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-turbo-260628": { + "cache_read_input_token_cost": 8.625e-08, + "input_cost_per_token": 4.3125e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.15625e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, "volcengine/doubao-seed-2-0-lite-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, @@ -58989,7 +59775,8 @@ "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_response_schema": true }, "fireworks_ai/accounts/fireworks/models/kimi-k3": { "cache_read_input_token_cost": 3e-07, @@ -59065,7 +59852,8 @@ "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_response_schema": true }, "fireworks_ai/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, @@ -62056,6 +62844,36 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": { "cache_read_input_token_cost": 3e-08, "cache_read_input_token_cost_priority": 3.75e-08, @@ -64225,9 +65043,9 @@ "supports_prompt_caching": true }, "openrouter/z-ai/glm-5.3-flash": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 5e-07, - "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 1.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 131072, @@ -64277,9 +65095,9 @@ "supports_prompt_caching": true }, "openrouter/qwen/qwen3.8-27b": { - "input_cost_per_token": 4.2e-07, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 8.5e-08, + "input_cost_per_token": 2.14e-07, + "output_cost_per_token": 2.55e-06, + "cache_read_input_token_cost": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 131072, @@ -64362,9 +65180,9 @@ "supports_prompt_caching": true }, "openrouter/deepseek/deepseek-v4-flash-0731": { - "input_cost_per_token": 6.5e-08, - "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.2e-07, + "cache_read_input_token_cost": 1.2e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, @@ -64432,9 +65250,9 @@ "supports_vision": false }, "openrouter/moonshotai/kimi-k3": { - "input_cost_per_token": 2.1e-06, - "output_cost_per_token": 1.053e-05, - "cache_read_input_token_cost": 2.35e-07, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 943718, @@ -64531,9 +65349,9 @@ "supports_prompt_caching": true }, "openrouter/z-ai/glm-5.2": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 131072, @@ -64564,9 +65382,9 @@ "supports_vision": false }, "openrouter/moonshotai/kimi-k2.7-code": { - "input_cost_per_token": 7.1e-07, - "output_cost_per_token": 3.5e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 7.062e-07, + "output_cost_per_token": 3.21e-06, + "cache_read_input_token_cost": 1.8e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 235929, @@ -64868,8 +65686,8 @@ "supports_prompt_caching": true }, "openrouter/google/gemma-4-26b-a4b-it": { - "input_cost_per_token": 4.2e-08, - "output_cost_per_token": 2.2e-07, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 16384, @@ -65416,8 +66234,8 @@ "supports_vision": true }, "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 5.2e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 16384, @@ -65677,8 +66495,8 @@ "supports_vision": false }, "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 4.815e-08, + "output_cost_per_token": 1.9305e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 32000, @@ -65737,7 +66555,7 @@ "supports_vision": false }, "openrouter/minimax/minimax-m1": { - "input_cost_per_token": 5.5e-07, + "input_cost_per_token": 4e-07, "output_cost_per_token": 2.2e-06, "litellm_provider": "openrouter", "max_input_tokens": 1000000, @@ -65876,8 +66694,8 @@ "supports_vision": false }, "openrouter/qwen/qwen3-14b": { - "input_cost_per_token": 2.275e-07, - "output_cost_per_token": 9.1e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 2.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 16384, @@ -65939,8 +66757,8 @@ "supports_prompt_caching": true }, "openrouter/meta-llama/llama-4-maverick": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6.96e-07, + "input_cost_per_token": 1.875e-07, + "output_cost_per_token": 6.525e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 115200, @@ -66361,14 +67179,6 @@ "supports_response_schema": true, "supports_vision": false }, - "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { - "cache_read_input_token_cost": 3.9e-07, - "input_cost_per_token": 2.1e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://api.fireworks.ai/v1/serverless/models" - }, "together_ai/arcee-ai/trinity-mini": { "input_cost_per_token": 4.5e-08, "litellm_provider": "together_ai", @@ -66408,14 +67218,6 @@ "output_cost_per_token": 1.6e-06, "source": "https://api.together.ai/v1/models" }, - "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" - }, "vertex_ai/gemini-2.5-flash-native-audio": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, diff --git a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py index 3f54b695fef..5795e29a8bc 100644 --- a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py +++ b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py @@ -5,12 +5,15 @@ from typing import NamedTuple import pytest import litellm +from litellm.cost_calculator import completion_cost from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig from litellm.llms.bedrock.common_utils import BedrockModelInfo from litellm.types.utils import ( Choices, Message, ModelResponse, + PromptTokensDetailsWrapper, + Usage, ) @@ -152,3 +155,55 @@ def test_bedrock_gpt_5_6_offers_tools_and_reasoning_effort_but_not_thinking(prof assert "reasoning_effort" in supported assert "thinking" not in supported assert "output_config" not in supported + + +# Cache-read prices are the `*-cache-read-input-tokens` usagetype rows of the AWS Price List API, us-east-1, +# https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json on 2026-09-15 +@pytest.mark.parametrize( + "model,expected_cache_read", + [ + ("amazon.nova-lite-v1:0", 1.5e-8), + ("us.amazon.nova-lite-v1:0", 1.5e-8), + ("amazon.nova-micro-v1:0", 8.75e-9), + ("us.amazon.nova-micro-v1:0", 8.75e-9), + ("amazon.nova-pro-v1:0", 2e-7), + ("us.amazon.nova-pro-v1:0", 2e-7), + ("us.amazon.nova-premier-v1:0", 6.25e-7), + ], +) +def test_bedrock_nova_cache_read_prices( + model, expected_cache_read, local_model_cost_map +): + model_info = litellm.model_cost[model] + assert model_info["cache_read_input_token_cost"] == expected_cache_read + usage = Usage( + prompt_tokens=1_000, + completion_tokens=100, + total_tokens=1_100, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=400), + ) + response = _bedrock_response(model, usage) + + cost = completion_cost( + completion_response=response, + model=model, + custom_llm_provider="bedrock", + ) + expected_cost = ( + 600 * model_info["input_cost_per_token"] + + 400 * expected_cache_read + + 100 * model_info["output_cost_per_token"] + ) + assert cost == pytest.approx(expected_cost) + + uncached_usage = Usage( + prompt_tokens=1_000, + completion_tokens=100, + total_tokens=1_100, + ) + uncached_cost = completion_cost( + completion_response=_bedrock_response(model, uncached_usage), + model=model, + custom_llm_provider="bedrock", + ) + assert cost < uncached_cost diff --git a/tests/test_litellm/llms/gemini/test_cost_calculator.py b/tests/test_litellm/llms/gemini/test_cost_calculator.py index 2d56757c601..5eed11dff03 100644 --- a/tests/test_litellm/llms/gemini/test_cost_calculator.py +++ b/tests/test_litellm/llms/gemini/test_cost_calculator.py @@ -1,8 +1,7 @@ -import os - import pytest import litellm +from litellm.cost_calculator import completion_cost from litellm.llms.gemini.cost_calculator import ( cost_per_google_maps_grounding_request, cost_per_web_search_request, @@ -18,6 +17,7 @@ from litellm.types.utils import ( ImageResponse, ImageUsage, ImageUsageInputTokensDetails, + ModelResponse, PromptTokensDetailsWrapper, Usage, ) @@ -452,6 +452,42 @@ def test_map_traffic_type_to_service_tier( ) +# Alias targets are the `modelVersion` returned by +# POST https://generativelanguage.googleapis.com/v1beta/models/:generateContent on 2026-09-15 +@pytest.mark.parametrize( + "alias,target", + [ + ("gemini/gemini-flash-latest", "gemini/gemini-3.8-flash"), + ("gemini/gemini-flash-lite-latest", "gemini/gemini-3.5-flash-lite"), + ("gemini/gemini-pro-latest", "gemini/gemini-3.1-pro-preview"), + ], +) +def test_latest_aliases_cost_the_same_as_their_current_target( + monkeypatch, alias, target +): + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url="")) + + usage = Usage( + prompt_tokens=1_000, + completion_tokens=500, + total_tokens=1_500, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=400), + ) + + def cost_of(model: str) -> float: + return completion_cost( + completion_response=ModelResponse(model=model, usage=usage), + model=model, + custom_llm_provider="gemini", + ) + + alias_cost = cost_of(alias) + target_cost = cost_of(target) + assert alias_cost == pytest.approx(target_cost) + assert alias_cost > 0 + + @pytest.mark.parametrize( "prefixed,bare", [ diff --git a/tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py b/tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py new file mode 100644 index 00000000000..72e98711f0c --- /dev/null +++ b/tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py @@ -0,0 +1,38 @@ +from typing import Final + +import pytest + +import litellm +from litellm import get_model_info +from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider +from litellm.utils import supports_prompt_caching + +MODEL: Final = "vertex_ai/xai/grok-4.6" +GROK_KEY_PREFIXES: Final = ("vertex_ai/xai/grok-", "azure_ai/grok-", "xai/grok-") + + +@pytest.mark.usefixtures("local_model_cost_map") +def test_grok_models_with_cache_read_price_advertise_prompt_caching() -> None: + cached_grok_models = tuple( + key + for key, entry in litellm.model_cost.items() + if key.startswith(GROK_KEY_PREFIXES) and entry.get("cache_read_input_token_cost") + ) + assert cached_grok_models, "expected at least one grok model with a cache read price" + + missing_flag = tuple(key for key in cached_grok_models if supports_prompt_caching(model=key) is not True) + assert missing_flag == (), ( + f"grok models with cache_read_input_token_cost fail supports_prompt_caching: {missing_flag}" + ) + + +@pytest.mark.usefixtures("local_model_cost_map") +def test_vertex_ai_grok_4_6_supports_prompt_caching_via_get_model_info() -> None: + routed_model, provider, _, _ = get_llm_provider(model=MODEL) + assert (routed_model, provider) == ("xai/grok-4.6", "vertex_ai") + + info = get_model_info(model=routed_model, custom_llm_provider=provider) + assert info["litellm_provider"] == "vertex_ai" + assert info.get("supports_prompt_caching") is True + + assert supports_prompt_caching(model=MODEL) is True