From 3c80351b57e2f6a184615ee5f939078214418678 Mon Sep 17 00:00:00 2001 From: Sameer Kankute Date: Fri, 6 Mar 2026 22:26:14 +0530 Subject: [PATCH] feat(openai): add 272K tier pricing for GPT-5.4/5.4-pro Prompts >272K input tokens priced at 2x input, 1.5x output for full session (standard, batch, flex). Applies to models with 1.05M context window (gpt-5.4, gpt-5.4-pro). - Add input/output_cost_per_token_above_272k_tokens to model_prices - Add above_272k fields to ModelInfoBase and get_model_info extraction - Add test_generic_cost_per_token_gpt54_above_272k_tokens Made-with: Cursor --- ...odel_prices_and_context_window_backup.json | 2476 ++++++++++++++--- litellm/types/utils.py | 71 +- litellm/utils.py | 9 + model_prices_and_context_window.json | 2476 ++++++++++++++--- .../llm_cost_calc/test_llm_cost_calc_utils.py | 28 +- tests/test_litellm/test_utils.py | 169 +- 6 files changed, 4414 insertions(+), 815 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 4bc2c663811..f1ca7cd83b7 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -143,7 +143,7 @@ "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" }, "mode": "image_generation", - "output_cost_per_image": 0.021, + "output_cost_per_image": 0.026, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -155,7 +155,7 @@ "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" }, "mode": "image_generation", - "output_cost_per_image": 0.042, + "output_cost_per_image": 0.052, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -167,7 +167,7 @@ "notes": "Flux Dev - Development version optimized for experimentation" }, "mode": "image_generation", - "output_cost_per_image": 0.053, + "output_cost_per_image": 0.065, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -176,7 +176,7 @@ "aiml/flux-pro/v1.1": { "litellm_provider": "aiml", "mode": "image_generation", - "output_cost_per_image": 0.042, + "output_cost_per_image": 0.052, "supported_endpoints": [ "/v1/images/generations" ] @@ -195,7 +195,7 @@ "notes": "Flux Pro - Professional-grade image generation model" }, "mode": "image_generation", - "output_cost_per_image": 0.037, + "output_cost_per_image": 0.046, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -207,7 +207,7 @@ "notes": "Flux Dev - Development version optimized for experimentation" }, "mode": "image_generation", - "output_cost_per_image": 0.026, + "output_cost_per_image": 0.033, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -219,7 +219,7 @@ "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "mode": "image_generation", - "output_cost_per_image": 0.084, + "output_cost_per_image": 0.104, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -231,7 +231,7 @@ "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "mode": "image_generation", - "output_cost_per_image": 0.042, + "output_cost_per_image": 0.052, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -243,7 +243,7 @@ "notes": "Flux Schnell - Fast generation model optimized for speed" }, "mode": "image_generation", - "output_cost_per_image": 0.003, + "output_cost_per_image": 0.004, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -255,7 +255,7 @@ "notes": "Imagen 4.0 Ultra Generate API - Photorealistic image generation with precise text rendering" }, "mode": "image_generation", - "output_cost_per_image": 0.063, + "output_cost_per_image": 0.078, "source": "https://docs.aimlapi.com/api-references/image-models/google/imagen-4-ultra-generate", "supported_endpoints": [ "/v1/images/generations" @@ -267,7 +267,7 @@ "notes": "Gemini 3 Pro Image (Nano Banana Pro) - Advanced text-to-image generation with reasoning and 4K resolution support" }, "mode": "image_generation", - "output_cost_per_image": 0.1575, + "output_cost_per_image": 0.195, "source": "https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview", "supported_endpoints": [ "/v1/images/generations" @@ -846,7 +846,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 3.125e-07 }, "anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, @@ -859,7 +861,9 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost": 1.875e-05 }, "anthropic.claude-3-sonnet-20240229-v1:0": { "input_cost_per_token": 3e-06, @@ -873,7 +877,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "anthropic.claude-instant-v1": { "input_cost_per_token": 8e-07, @@ -1233,7 +1239,7 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, - "apac.anthropic.claude-sonnet-4-6": { + "au.anthropic.claude-sonnet-4-6": { "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_read_input_token_cost": 3.3e-07, @@ -1512,7 +1518,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -1545,7 +1553,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 3.125e-07 }, "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -1581,7 +1591,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -3040,6 +3052,37 @@ "supports_tool_choice": true, "supports_vision": false }, + "azure/gpt-audio-1.5-2026-02-23": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure/gpt-audio-mini-2025-10-06": { "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, @@ -3216,6 +3259,38 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "azure/gpt-realtime-1.5-2026-02-23": { + "cache_creation_input_audio_token_cost": 4e-06, + "cache_read_input_token_cost": 4e-06, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "azure/gpt-realtime-mini-2025-10-06": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, @@ -4124,6 +4199,36 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.4e-05, + "supported_endpoints": [ + "/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 + }, "azure/gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, "litellm_provider": "azure", @@ -5712,6 +5817,15 @@ ], "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry" }, + "azure_ai/mistral-document-ai-2512": { + "litellm_provider": "azure_ai", + "ocr_cost_per_page": 0.003, + "mode": "ocr", + "supported_endpoints": [ + "/v1/ocr" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/" + }, "azure_ai/doc-intelligence/prebuilt-read": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.0015, @@ -6129,13 +6243,13 @@ "supports_tool_choice": true }, "azure_ai/mistral-small-2503": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -6832,7 +6946,9 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 4.45e-06, @@ -7251,7 +7367,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3.6e-07, + "cache_creation_input_token_cost": 4.5e-06 }, "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { "input_cost_per_token": 3e-07, @@ -7265,7 +7383,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07 }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { "input_cost_per_token": 3.3e-06, @@ -7283,7 +7403,9 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3.3e-07, + "cache_creation_input_token_cost": 4.125e-06 }, "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -7396,7 +7518,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3.6e-07, + "cache_creation_input_token_cost": 4.5e-06 }, "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { "input_cost_per_token": 3e-07, @@ -7410,7 +7534,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07 }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { "input_cost_per_token": 3.3e-06, @@ -7428,7 +7554,9 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3.3e-07, + "cache_creation_input_token_cost": 4.125e-06 }, "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -8295,37 +8423,6 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, - "us/claude-sonnet-4-6": { - "cache_creation_input_token_cost": 4.125e-06, - "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, - "cache_read_input_token_cost": 3.3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, - "input_cost_per_token": 3.3e-06, - "input_cost_per_token_above_200k_tokens": 6.6e-06, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.65e-05, - "output_cost_per_token_above_200k_tokens": 2.475e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "inference_geo": "us" - }, "claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, @@ -8517,100 +8614,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "fast/claude-opus-4-6": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_200k_tokens": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, - "input_cost_per_token": 3e-05, - "input_cost_per_token_above_200k_tokens": 1e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_above_200k_tokens": 3.75e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "us/claude-opus-4-6": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_200k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_1hr": 1.1e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1.1e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_200k_tokens": 1.1e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-05, - "output_cost_per_token_above_200k_tokens": 4.125e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "fast/us/claude-opus-4-6": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_200k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_1hr": 1.1e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1.1e-06, - "input_cost_per_token": 3e-05, - "input_cost_per_token_above_200k_tokens": 1.1e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_above_200k_tokens": 4.125e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "tool_use_system_prompt_tokens": 346, + "provider_specific_entry": { + "us": 1.1, + "fast": 6.0 + } }, "claude-opus-4-6-20260205": { "cache_creation_input_token_cost": 6.25e-06, @@ -8641,69 +8649,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "fast/claude-opus-4-6-20260205": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_200k_tokens": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, - "input_cost_per_token": 3e-05, - "input_cost_per_token_above_200k_tokens": 1e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_above_200k_tokens": 3.75e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "us/claude-opus-4-6-20260205": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_200k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_1hr": 1.1e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1.1e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_200k_tokens": 1.1e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-05, - "output_cost_per_token_above_200k_tokens": 4.125e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "tool_use_system_prompt_tokens": 346, + "provider_specific_entry": { + "us": 1.1, + "fast": 6.0 + } }, "claude-sonnet-4-20250514": { "deprecation_date": "2026-05-14", @@ -9838,6 +9788,190 @@ } ] }, + "dashscope/qwen3-max-2026-01-23": { + "litellm_provider": "dashscope", + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "dashscope/qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "dashscope/qwen3-next-80b-a3b-thinking": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen3-vl-235b-a22b-thinking": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen3-vl-32b-instruct": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.4e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen3-vl-32b-thinking": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.87e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen3-vl-plus": { + "litellm_provider": "dashscope", + "max_input_tokens": 260096, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.4e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 4.8e-06, + "range": [ + 128000.0, + 256000.0 + ] + } + ] + }, + "dashscope/qwen3.5-plus": { + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2.4e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, "dashscope/qwq-plus": { "input_cost_per_token": 8e-07, "litellm_provider": "dashscope", @@ -10835,7 +10969,8 @@ "output_cost_per_token": 9e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { "max_tokens": 131072, @@ -10845,7 +10980,8 @@ "output_cost_per_token": 1e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { "max_tokens": 131072, @@ -10865,7 +11001,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen2.5-72B-Instruct": { "max_tokens": 32768, @@ -10875,7 +11012,8 @@ "output_cost_per_token": 3.9e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { "max_tokens": 32768, @@ -10896,7 +11034,8 @@ "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-14B": { "max_tokens": 40960, @@ -10906,7 +11045,8 @@ "output_cost_per_token": 2.4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B": { "max_tokens": 40960, @@ -10916,7 +11056,8 @@ "output_cost_per_token": 5.4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { "max_tokens": 262144, @@ -10926,7 +11067,8 @@ "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { "max_tokens": 262144, @@ -10936,7 +11078,8 @@ "output_cost_per_token": 2.9e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-30B-A3B": { "max_tokens": 40960, @@ -10946,7 +11089,8 @@ "output_cost_per_token": 2.9e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-32B": { "max_tokens": 40960, @@ -10956,7 +11100,8 @@ "output_cost_per_token": 2.8e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { "max_tokens": 262144, @@ -10966,7 +11111,8 @@ "output_cost_per_token": 1.6e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { "max_tokens": 262144, @@ -10976,7 +11122,8 @@ "output_cost_per_token": 1.2e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { "max_tokens": 262144, @@ -10986,7 +11133,8 @@ "output_cost_per_token": 1.4e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { "max_tokens": 262144, @@ -10996,7 +11144,8 @@ "output_cost_per_token": 1.4e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { "max_tokens": 8192, @@ -11047,7 +11196,8 @@ "cache_read_input_token_cost": 3.3e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/anthropic/claude-4-opus": { "max_tokens": 200000, @@ -11057,7 +11207,8 @@ "output_cost_per_token": 8.25e-05, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/anthropic/claude-4-sonnet": { "max_tokens": 200000, @@ -11067,7 +11218,8 @@ "output_cost_per_token": 1.65e-05, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1": { "max_tokens": 163840, @@ -11077,7 +11229,8 @@ "output_cost_per_token": 2.4e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528": { "max_tokens": 163840, @@ -11088,7 +11241,8 @@ "cache_read_input_token_cost": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { "max_tokens": 32768, @@ -11098,7 +11252,8 @@ "output_cost_per_token": 3e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { "max_tokens": 131072, @@ -11118,7 +11273,8 @@ "output_cost_per_token": 2.7e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { "max_tokens": 40960, @@ -11128,7 +11284,8 @@ "output_cost_per_token": 3e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3": { "max_tokens": 163840, @@ -11138,7 +11295,8 @@ "output_cost_per_token": 8.9e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { "max_tokens": 163840, @@ -11148,7 +11306,8 @@ "output_cost_per_token": 8.8e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { "max_tokens": 163840, @@ -11160,7 +11319,8 @@ "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { "max_tokens": 163840, @@ -11171,10 +11331,11 @@ "cache_read_input_token_cost": 2.16e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -11182,7 +11343,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemini-2.5-flash": { "max_tokens": 1000000, @@ -11192,7 +11354,8 @@ "output_cost_per_token": 2.5e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemini-2.5-pro": { "max_tokens": 1000000, @@ -11202,7 +11365,8 @@ "output_cost_per_token": 1e-05, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemma-3-12b-it": { "max_tokens": 131072, @@ -11212,7 +11376,8 @@ "output_cost_per_token": 1e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemma-3-27b-it": { "max_tokens": 131072, @@ -11222,7 +11387,8 @@ "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemma-3-4b-it": { "max_tokens": 131072, @@ -11232,7 +11398,8 @@ "output_cost_per_token": 8e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { "max_tokens": 131072, @@ -11252,7 +11419,8 @@ "output_cost_per_token": 2e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { "max_tokens": 131072, @@ -11262,7 +11430,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { "max_tokens": 131072, @@ -11272,6 +11441,7 @@ "output_cost_per_token": 3.9e-07, "litellm_provider": "deepinfra", "mode": "chat", + "supports_function_calling": true, "supports_tool_choice": true }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { @@ -11282,7 +11452,8 @@ "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "max_tokens": 327680, @@ -11292,7 +11463,8 @@ "output_cost_per_token": 3e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Llama-Guard-3-8B": { "max_tokens": 131072, @@ -11322,7 +11494,8 @@ "output_cost_per_token": 6e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { "max_tokens": 131072, @@ -11332,7 +11505,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { "max_tokens": 131072, @@ -11342,7 +11516,8 @@ "output_cost_per_token": 2.8e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { "max_tokens": 131072, @@ -11352,7 +11527,8 @@ "output_cost_per_token": 5e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { "max_tokens": 131072, @@ -11362,7 +11538,8 @@ "output_cost_per_token": 3e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/microsoft/WizardLM-2-8x22B": { "max_tokens": 65536, @@ -11382,7 +11559,8 @@ "output_cost_per_token": 1.4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { "max_tokens": 131072, @@ -11392,7 +11570,8 @@ "output_cost_per_token": 4e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { "max_tokens": 32768, @@ -11402,7 +11581,8 @@ "output_cost_per_token": 8e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { "max_tokens": 128000, @@ -11412,7 +11592,8 @@ "output_cost_per_token": 2e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { "max_tokens": 32768, @@ -11422,7 +11603,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct": { "max_tokens": 131072, @@ -11432,7 +11614,8 @@ "output_cost_per_token": 2e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct-0905": { "max_tokens": 262144, @@ -11443,7 +11626,8 @@ "cache_read_input_token_cost": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { "max_tokens": 131072, @@ -11453,7 +11637,8 @@ "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": { "max_tokens": 131072, @@ -11463,7 +11648,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { "max_tokens": 131072, @@ -11473,7 +11659,8 @@ "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/openai/gpt-oss-120b": { "max_tokens": 131072, @@ -11483,7 +11670,8 @@ "output_cost_per_token": 4.5e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/openai/gpt-oss-20b": { "max_tokens": 131072, @@ -11493,7 +11681,8 @@ "output_cost_per_token": 1.5e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/zai-org/GLM-4.5": { "max_tokens": 131072, @@ -11503,7 +11692,8 @@ "output_cost_per_token": 1.6e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepseek/deepseek-chat": { "cache_creation_input_token_cost": 0.0, @@ -12035,7 +12225,9 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 3.125e-07 }, "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -12072,7 +12264,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-3-5-sonnet-20241022-v2:0": { "input_cost_per_token": 3e-06, @@ -12089,7 +12283,9 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": { "input_cost_per_token": 3e-06, @@ -12107,7 +12303,9 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-3-haiku-20240307-v1:0": { "input_cost_per_token": 2.5e-07, @@ -12121,7 +12319,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 3.125e-07 }, "eu.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, @@ -12134,7 +12334,9 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost": 1.875e-05 }, "eu.anthropic.claude-3-sonnet-20240229-v1:0": { "input_cost_per_token": 3e-06, @@ -12148,7 +12350,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -13675,7 +13879,7 @@ }, "gemini-2.0-flash": { "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-language-models", @@ -13715,7 +13919,7 @@ }, "gemini-2.0-flash-001": { "cache_read_input_token_cost": 3.75e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-language-models", @@ -13801,7 +14005,7 @@ }, "gemini-2.0-flash-lite": { "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "vertex_ai-language-models", @@ -13837,7 +14041,7 @@ }, "gemini-2.0-flash-lite-001": { "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "vertex_ai-language-models", @@ -14279,6 +14483,89 @@ "supports_vision": true, "supports_web_search": true }, + "gemini-3.1-flash-image-preview": { + "input_cost_per_image": 0.00056, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0672, + "output_cost_per_image_token": 6e-05, + "output_cost_per_token": 3e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "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_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true + }, "deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -14462,13 +14749,12 @@ "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" + "/vertex_ai/live" ], "supported_modalities": [ "text", @@ -14507,14 +14793,13 @@ "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" + "/v1/realtime" ], "supported_modalities": [ "text", @@ -14722,6 +15007,7 @@ "supports_web_search": true }, "gemini-3-pro-preview": { + "deprecation_date": "2026-03-26", "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, @@ -14768,7 +15054,14 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, @@ -14819,7 +15112,14 @@ "supports_vision": true, "supports_web_search": true, "supports_url_context": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "gemini-3.1-pro-preview-customtools": { "cache_read_input_token_cost": 2e-07, @@ -14919,7 +15219,14 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "vertex_ai/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, @@ -14963,7 +15270,12 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 9e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "output_cost_per_token_priority": 5.4e-06, + "cache_read_input_token_cost_priority": 9e-08, + "supports_service_tier": true }, "vertex_ai/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, @@ -15014,7 +15326,14 @@ "supports_vision": true, "supports_web_search": true, "supports_url_context": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "vertex_ai/gemini-3.1-pro-preview-customtools": { "cache_read_input_token_cost": 2e-07, @@ -15065,7 +15384,14 @@ "supports_vision": true, "supports_web_search": true, "supports_url_context": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "gemini-2.5-pro-exp-03-25": { "cache_read_input_token_cost": 1.25e-07, @@ -15818,7 +16144,7 @@ }, "gemini/gemini-2.0-flash": { "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", @@ -15859,7 +16185,7 @@ }, "gemini/gemini-2.0-flash-001": { "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", @@ -15947,7 +16273,7 @@ }, "gemini/gemini-2.0-flash-lite": { "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "gemini", @@ -15983,7 +16309,7 @@ "tpm": 4000000 }, "gemini/gemini-2.0-flash-lite-preview-02-05": { - "deprecation_date": "2025-12-02", + "deprecation_date": "2025-12-09", "cache_read_input_token_cost": 1.875e-08, "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, @@ -16302,7 +16628,7 @@ "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, - "litellm_provider": "vertex_ai-language-models", + "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "supports_reasoning": false, @@ -16860,6 +17186,8 @@ "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, + "input_cost_per_token_priority": 1.25e-06, + "input_cost_per_token_above_200k_tokens_priority": 2.5e-06, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, @@ -16873,8 +17201,11 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token_priority": 1e-05, + "output_cost_per_token_above_200k_tokens_priority": 1.5e-05, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_service_tier": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -16933,6 +17264,7 @@ "tpm": 800000 }, "gemini/gemini-3-pro-preview": { + "deprecation_date": "2026-03-09", "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 2e-06, @@ -16979,7 +17311,67 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "tpm": 800000 + "tpm": 800000, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true + }, + "gemini/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "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_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 250000 }, "gemini/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, @@ -17027,7 +17419,12 @@ "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, - "tpm": 800000 + "tpm": 800000, + "input_cost_per_token_priority": 9e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "output_cost_per_token_priority": 5.4e-06, + "cache_read_input_token_cost_priority": 9e-08, + "supports_service_tier": true }, "gemini/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, @@ -17078,7 +17475,14 @@ "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, - "tpm": 800000 + "tpm": 800000, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "gemini/gemini-3.1-pro-preview-customtools": { "cache_read_input_token_cost": 2e-07, @@ -17129,7 +17533,14 @@ "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, - "tpm": 800000 + "tpm": 800000, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, @@ -17175,7 +17586,12 @@ "supports_url_context": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 9e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "output_cost_per_token_priority": 5.4e-06, + "cache_read_input_token_cost_priority": 9e-08, + "supports_service_tier": true }, "gemini/gemini-2.5-pro-exp-03-25": { "cache_read_input_token_cost": 0.0, @@ -18021,6 +18437,93 @@ "max_tokens": 8191, "mode": "embedding" }, + "chatgpt/gpt-5.4": { + "litellm_provider": "chatgpt", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.4-pro": { + "litellm_provider": "chatgpt", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.3-codex": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.3-codex-spark": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.3-instant": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.3-chat-latest": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, "chatgpt/gpt-5.2-codex": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, @@ -19187,6 +19690,39 @@ "supports_tool_choice": true, "supports_vision": false }, + "gpt-audio-1.5": { + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "gpt-audio-2025-08-28": { "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, @@ -20057,7 +20593,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5.1": { "cache_read_input_token_cost": 1.25e-07, @@ -20093,7 +20631,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": false }, "gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -20129,7 +20669,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": false }, "gpt-5.1-chat-latest": { "cache_read_input_token_cost": 1.25e-07, @@ -20164,7 +20706,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": false }, "gpt-5.2": { "cache_read_input_token_cost": 1.75e-07, @@ -20201,7 +20745,10 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true }, "gpt-5.2-2025-12-11": { "cache_read_input_token_cost": 1.75e-07, @@ -20238,7 +20785,10 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true }, "gpt-5.2-chat-latest": { "cache_read_input_token_cost": 1.75e-07, @@ -20272,7 +20822,47 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false, + "supports_web_search": true + }, + "gpt-5.3-chat-latest": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/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_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false, + "supports_web_search": true }, "gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, @@ -20303,7 +20893,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true }, "gpt-5.2-pro-2025-12-11": { "input_cost_per_token": 2.1e-05, @@ -20334,20 +20926,72 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true }, "gpt-5.4": { "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_priority": 5e-06, + "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_cost_per_token_priority": 2.25e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.375e-05, + "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_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-5.4-2026-03-05": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "input_cost_per_token_priority": 5e-06, + "input_cost_per_token_above_272k_tokens_priority": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "output_cost_per_token_priority": 2.25e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.375e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -20372,18 +21016,24 @@ "supports_service_tier": true, "supports_vision": true }, - "gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_priority": 5e-07, - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_priority": 5e-06, + "gpt-5.4-pro": { + "cache_read_input_token_cost": 3e-06, + "cache_read_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost_priority": 6e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05, + "input_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_priority": 6e-05, + "input_cost_per_token_above_272k_tokens_priority": 1.2e-04, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_priority": 2.25e-05, + "output_cost_per_token": 1.8e-04, + "output_cost_per_token_above_272k_tokens": 2.7e-04, + "output_cost_per_token_priority": 2.7e-04, + "output_cost_per_token_above_272k_tokens_priority": 4.05e-04, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -20402,11 +21052,59 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true + }, + "gpt-5.4-pro-2026-03-05": { + "cache_read_input_token_cost": 3e-06, + "cache_read_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost_priority": 6e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05, + "input_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_priority": 6e-05, + "input_cost_per_token_above_272k_tokens_priority": 1.2e-04, + "litellm_provider": "openai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.8e-04, + "output_cost_per_token_above_272k_tokens": 2.7e-04, + "output_cost_per_token_priority": 2.7e-04, + "output_cost_per_token_above_272k_tokens_priority": 4.05e-04, + "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": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true }, "gpt-5-pro": { "input_cost_per_token": 1.5e-05, @@ -20439,7 +21137,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-pro-2025-10-06": { "input_cost_per_token": 1.5e-05, @@ -20472,7 +21172,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, @@ -20511,7 +21213,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -20543,7 +21247,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-chat-latest": { "cache_read_input_token_cost": 1.25e-07, @@ -20575,7 +21281,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, @@ -20605,7 +21313,9 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5.1-codex": { "cache_read_input_token_cost": 1.25e-07, @@ -20638,7 +21348,9 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.25e-07, @@ -20668,7 +21380,9 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true }, "gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.5e-08, @@ -20701,7 +21415,9 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, @@ -20734,7 +21450,44 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true + }, + "gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/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": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-mini": { "cache_read_input_token_cost": 2.5e-08, @@ -20773,7 +21526,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, @@ -20812,7 +21567,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-nano": { "cache_read_input_token_cost": 5e-09, @@ -20848,7 +21605,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-09, @@ -20883,7 +21642,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-image-1": { "cache_read_input_image_token_cost": 2.5e-06, @@ -20943,6 +21704,38 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-realtime-1.5": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "gpt-realtime-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, @@ -21412,6 +22205,21 @@ "supports_tool_choice": true, "supports_web_search": true }, + "groq/openai/gpt-oss-safeguard-20b": { + "cache_read_input_token_cost": 3.7e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true + }, "groq/playai-tts": { "input_cost_per_character": 5e-05, "litellm_provider": "groq", @@ -22727,6 +23535,19 @@ "max_input_tokens": 200000, "max_output_tokens": 8192 }, + "mistral.devstral-2-123b": { + "input_cost_per_token": 4e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "mistral.magistral-small-2509": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock_converse", @@ -23048,6 +23869,21 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/magistral-medium-1-2-2509": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "mistral/mistral-ocr-latest": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.001, @@ -23113,6 +23949,21 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/magistral-small-1-2-2509": { + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "mistral/mistral-embed": { "input_cost_per_token": 1e-07, "litellm_provider": "mistral", @@ -23174,24 +24025,41 @@ "supports_tool_choice": true }, "mistral/mistral-large-latest": { - "input_cost_per_token": 2e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 6e-06, + "output_cost_per_token": 1.5e-06, + "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "mistral/mistral-large-3": { "input_cost_per_token": 5e-07, "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-large-2512": { + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -23242,14 +24110,30 @@ "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 131072, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-medium-3-1-2508": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://mistral.ai/news/mistral-medium-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "mistral/mistral-small": { "input_cost_per_token": 1e-07, @@ -23265,17 +24149,79 @@ "supports_tool_choice": true }, "mistral/mistral-small-latest": { - "input_cost_per_token": 1e-07, + "input_cost_per_token": 6e-08, "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 1.8e-07, + "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-small-3-2-2506": { + "input_cost_per_token": 6e-08, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-3-3b-2512": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-3-8b-2512": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-3-14b-2512": { + "input_cost_per_token": 2e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "mistral/mistral-tiny": { "input_cost_per_token": 2.5e-07, @@ -23927,6 +24873,335 @@ "/v1/images/generations" ] }, + "nebius/deepseek-ai/DeepSeek-R1": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/deepseek-ai/DeepSeek-R1-0528": { + "max_tokens": 164000, + "max_input_tokens": 164000, + "max_output_tokens": 164000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 7.5e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/deepseek-ai/DeepSeek-V3": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/deepseek-ai/DeepSeek-V3-0324": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/google/gemma-3-27b-it": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Llama-3.3-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Llama-Guard-3-8B": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "nebius", + "mode": "chat", + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/mistralai/Mistral-Nemo-Instruct-2407": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 1.2e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen3-235B-A22B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen3-32B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen3-30B-A3B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen3-14B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen3-4B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/QwQ-32B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 4.5e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2.5-72B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2.5-32B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2.5-Coder-7B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 3e-08, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2-VL-72B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2-VL-7B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/BAAI/bge-en-icl": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/BAAI/bge-multilingual-gemma2": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/intfloat/e5-mistral-7b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://nebius.com/prices-ai-studio" + }, "nvidia.nemotron-nano-12b-v2": { "input_cost_per_token": 2e-07, "litellm_provider": "bedrock_converse", @@ -25074,6 +26349,30 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, + "openrouter/anthropic/claude-sonnet-4.6": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, "openrouter/anthropic/claude-opus-4.5": { "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, @@ -25093,6 +26392,25 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, + "openrouter/anthropic/claude-opus-4.6": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 + }, "openrouter/anthropic/claude-sonnet-4.5": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 3.75e-06, @@ -25245,7 +26563,7 @@ "supports_tool_choice": true }, "openrouter/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", @@ -25405,6 +26723,39 @@ "supports_web_search": true, "tpm": 800000 }, + "openrouter/google/gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "source": "https://openrouter.ai/google/gemini-3.1-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_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 + }, "openrouter/gryphe/mythomax-l2-13b": { "input_cost_per_token": 1.875e-06, "litellm_provider": "openrouter", @@ -25782,6 +27133,29 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "openrouter/openai/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://openrouter.ai/openai/gpt-5.1-codex-max", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, "openrouter/openai/gpt-5.2": { "input_cost_per_image": 0, "cache_read_input_token_cost": 1.75e-07, @@ -25936,6 +27310,19 @@ "supports_tool_choice": true, "supports_function_calling": true }, + "openrouter/qwen/qwen3-coder-plus": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/qwen/qwen3-coder-plus", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "openrouter/qwen/qwen3-235b-a22b-2507": { "input_cost_per_token": 7.1e-08, "litellm_provider": "openrouter", @@ -26071,6 +27458,19 @@ "supports_vision": true, "supports_prompt_caching": false }, + "openrouter/z-ai/glm-5": { + "input_cost_per_token": 8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.56e-06, + "source": "https://openrouter.ai/z-ai/glm-5", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "openrouter/minimax/minimax-m2.1": { "input_cost_per_token": 2.7e-07, "output_cost_per_token": 1.2e-06, @@ -26105,6 +27505,42 @@ "supports_prompt_caching": true, "supports_computer_use": false }, + "openrouter/openrouter/auto": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 2000000, + "max_tokens": 2000000, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true + }, + "openrouter/openrouter/free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/openrouter/bodybuilder": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat" + }, "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", @@ -26651,8 +28087,8 @@ "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", - "supports_function_calling": true, - "supports_tool_choice": true + "supports_function_calling": false, + "supports_tool_choice": false }, "publicai/swiss-ai/apertus-70b-instruct": { "input_cost_per_token": 0.0, @@ -26663,8 +28099,8 @@ "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", - "supports_function_calling": true, - "supports_tool_choice": true + "supports_function_calling": false, + "supports_tool_choice": false }, "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT": { "input_cost_per_token": 0.0, @@ -26714,65 +28150,144 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "perplexity/preset/fast-search": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_preset": true, + "supports_function_calling": true + }, "perplexity/preset/pro-search": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_preset": true + "supports_preset": true, + "supports_function_calling": true }, - "perplexity/openai/gpt-4o": { + "perplexity/preset/deep-research": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_preset": true, + "supports_function_calling": true }, - "perplexity/openai/gpt-4o-mini": { + "perplexity/preset/advanced-deep-research": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_preset": true, + "supports_function_calling": true }, "perplexity/openai/gpt-5.2": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true }, - "perplexity/anthropic/claude-3-5-sonnet-20241022": { + "perplexity/openai/gpt-5.1": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_reasoning": false, + "supports_function_calling": true }, - "perplexity/anthropic/claude-3-5-haiku-20241022": { + "perplexity/openai/gpt-5-mini": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_reasoning": false, + "supports_function_calling": true }, - "perplexity/google/gemini-2.0-flash-exp": { + "perplexity/anthropic/claude-opus-4-6": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_reasoning": false, + "supports_function_calling": true }, - "perplexity/google/gemini-2.0-flash-thinking-exp": { + "perplexity/anthropic/claude-opus-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": true + "supports_reasoning": false, + "supports_function_calling": true }, - "perplexity/xai/grok-2-1212": { + "perplexity/anthropic/claude-sonnet-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_reasoning": false, + "supports_function_calling": true }, - "perplexity/xai/grok-2-vision-1212": { + "perplexity/anthropic/claude-haiku-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/google/gemini-3-pro-preview": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/google/gemini-3-flash-preview": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/google/gemini-2.5-pro": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/google/gemini-2.5-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/xai/grok-4-1-fast-non-reasoning": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/perplexity/sonar": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/pplx-embed-v1-0.6b": { + "input_cost_per_token": 4e-09, + "litellm_provider": "perplexity", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.perplexity.ai/docs/embeddings/quickstart" + }, + "perplexity/pplx-embed-v1-4b": { + "input_cost_per_token": 3e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2560, + "source": "https://docs.perplexity.ai/docs/embeddings/quickstart" }, "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT": { "input_cost_per_token": 0.0, @@ -28870,6 +30385,18 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/Qwen/Qwen3.5-397B-A17B": { + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "tts-1": { "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", @@ -29027,7 +30554,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -29080,7 +30609,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 3.125e-07 }, "us.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, @@ -29093,7 +30624,9 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost": 1.875e-05 }, "us.anthropic.claude-3-sonnet-20240229-v1:0": { "input_cost_per_token": 3e-06, @@ -29107,7 +30640,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "us.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -30000,7 +31535,7 @@ "supports_tool_choice": true }, "vercel_ai_gateway/google/gemini-2.0-flash": { - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, @@ -30014,7 +31549,7 @@ "supports_response_schema": true }, "vercel_ai_gateway/google/gemini-2.0-flash-lite": { - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_token": 7.5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, @@ -31519,6 +33054,70 @@ "output_cost_per_token_batches": 6e-06, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" }, + "vertex_ai/gemini-3.1-flash-image-preview": { + "input_cost_per_image": 0.00056, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0672, + "output_cost_per_image_token": 6e-05, + "output_cost_per_token": 3e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" + }, + "vertex_ai/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "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_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true + }, "vertex_ai/deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -32920,6 +34519,7 @@ "supports_web_search": true }, "xai/grok-2-vision-1212": { + "deprecation_date": "2026-02-28", "input_cost_per_image": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "xai", @@ -33024,6 +34624,7 @@ }, "xai/grok-3-mini": { "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-02-28", "input_cost_per_token": 3e-07, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33040,6 +34641,7 @@ }, "xai/grok-3-mini-beta": { "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-02-28", "input_cost_per_token": 3e-07, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33374,6 +34976,50 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "zai.glm-4.7-flash": { + "input_cost_per_token": 7e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "zai/glm-5": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3.2e-06, + "litellm_provider": "zai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "mode": "chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing" + }, + "zai/glm-5-code": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 5e-06, + "litellm_provider": "zai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "mode": "chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing" + }, "zai/glm-4.7": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1.1e-07, @@ -37158,7 +38804,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-search-api-2025-10-14": { "cache_read_input_token_cost": 1.25e-07, @@ -37177,7 +38825,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-realtime-mini-2025-10-06": { "cache_creation_input_audio_token_cost": 3e-07, @@ -37355,7 +39005,7 @@ }, "gemini/gemini-2.0-flash-lite-001": { "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "gemini", @@ -37820,5 +39470,59 @@ "metadata": { "notes": "DuckDuckGo Instant Answer API is free and does not require an API key." } + }, + "bedrock_mantle/openai.gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/openai.gpt-oss-20b": { + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 3e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/openai.gpt-oss-safeguard-120b": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/openai.gpt-oss-safeguard-20b": { + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 3e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true } } diff --git a/litellm/types/utils.py b/litellm/types/utils.py index 7760a894c7e..3f64bba7ced 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -1,47 +1,61 @@ import json import time from enum import Enum -from typing import (TYPE_CHECKING, Any, Dict, List, Literal, Mapping, Optional, - Union) +from typing import TYPE_CHECKING, Any, Dict, List, Literal, Mapping, Optional, Union from openai._models import BaseModel as OpenAIObject -from openai.types.audio.transcription_create_params import \ - FileTypes as FileTypes # type: ignore +from openai.types.audio.transcription_create_params import ( + FileTypes as FileTypes, # type: ignore +) from openai.types.chat.chat_completion import ChatCompletion as ChatCompletion -from openai.types.completion_usage import (CompletionTokensDetails, - CompletionUsage, - PromptTokensDetails) +from openai.types.completion_usage import ( + CompletionTokensDetails, + CompletionUsage, + PromptTokensDetails, +) from openai.types.moderation import Categories as Categories -from openai.types.moderation import \ - CategoryAppliedInputTypes as CategoryAppliedInputTypes +from openai.types.moderation import ( + CategoryAppliedInputTypes as CategoryAppliedInputTypes, +) from openai.types.moderation import CategoryScores as CategoryScores from openai.types.moderation_create_response import Moderation as Moderation -from openai.types.moderation_create_response import \ - ModerationCreateResponse as ModerationCreateResponse +from openai.types.moderation_create_response import ( + ModerationCreateResponse as ModerationCreateResponse, +) from pydantic import BaseModel, ConfigDict, Field, PrivateAttr, model_validator from typing_extensions import Required, TypedDict from litellm._uuid import uuid -from litellm.types.llms.base import (BaseLiteLLMOpenAIResponseObject, - LiteLLMPydanticObjectBase) +from litellm.types.llms.base import ( + BaseLiteLLMOpenAIResponseObject, + LiteLLMPydanticObjectBase, +) from litellm.types.mcp import MCPServerCostInfo from ..litellm_core_utils.core_helpers import map_finish_reason from .agents import LiteLLMSendMessageResponse from .guardrails import GuardrailEventHooks -from .llms.anthropic_messages.anthropic_response import \ - AnthropicMessagesResponse +from .llms.anthropic_messages.anthropic_response import AnthropicMessagesResponse from .llms.base import HiddenParams -from .llms.openai import (AllMessageValues, Batch, ChatCompletionAnnotation, - ChatCompletionRedactedThinkingBlock, - ChatCompletionThinkingBlock, - ChatCompletionToolCallChunk, ChatCompletionToolParam, - ChatCompletionUsageBlock, FileSearchTool, - FineTuningJob, ImageURLListItem, - OpenAIChatCompletionChunk, - OpenAIChatCompletionFinishReason, OpenAIFileObject, - OpenAIRealtimeStreamList, ResponsesAPIResponse, - WebSearchOptions) +from .llms.openai import ( + AllMessageValues, + Batch, + ChatCompletionAnnotation, + ChatCompletionRedactedThinkingBlock, + ChatCompletionThinkingBlock, + ChatCompletionToolCallChunk, + ChatCompletionToolParam, + ChatCompletionUsageBlock, + FileSearchTool, + FineTuningJob, + ImageURLListItem, + OpenAIChatCompletionChunk, + OpenAIChatCompletionFinishReason, + OpenAIFileObject, + OpenAIRealtimeStreamList, + ResponsesAPIResponse, + WebSearchOptions, +) from .rerank import RerankResponse as RerankResponse if TYPE_CHECKING: @@ -150,12 +164,16 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): float ] # OpenAI priority service tier pricing cache_read_input_token_cost_above_200k_tokens: Optional[float] + cache_read_input_token_cost_above_272k_tokens: Optional[float] input_cost_per_character: Optional[float] # only for vertex ai models input_cost_per_audio_token: Optional[float] input_cost_per_token_above_128k_tokens: Optional[float] # only for vertex ai models input_cost_per_token_above_200k_tokens: Optional[ float ] # only for vertex ai gemini-2.5-pro models + input_cost_per_token_above_272k_tokens: Optional[ + float + ] # GPT-5.4/5.4-pro: prompts >272K priced at 2x input input_cost_per_character_above_128k_tokens: Optional[ float ] # only for vertex ai models @@ -180,6 +198,9 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False): output_cost_per_token_above_200k_tokens: Optional[ float ] # only for vertex ai gemini-2.5-pro models + output_cost_per_token_above_272k_tokens: Optional[ + float + ] # GPT-5.4/5.4-pro: prompts >272K priced at 1.5x output output_cost_per_character_above_128k_tokens: Optional[ float ] # only for vertex ai models diff --git a/litellm/utils.py b/litellm/utils.py index 4771219d111..3742638a26c 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -5599,6 +5599,9 @@ def _get_model_info_helper( # noqa: PLR0915 cache_read_input_token_cost_above_200k_tokens=_model_info.get( "cache_read_input_token_cost_above_200k_tokens", None ), + cache_read_input_token_cost_above_272k_tokens=_model_info.get( + "cache_read_input_token_cost_above_272k_tokens", None + ), cache_read_input_token_cost_flex=_model_info.get( "cache_read_input_token_cost_flex", None ), @@ -5617,6 +5620,9 @@ def _get_model_info_helper( # noqa: PLR0915 input_cost_per_token_above_200k_tokens=_model_info.get( "input_cost_per_token_above_200k_tokens", None ), + input_cost_per_token_above_272k_tokens=_model_info.get( + "input_cost_per_token_above_272k_tokens", None + ), input_cost_per_query=_model_info.get("input_cost_per_query", None), input_cost_per_second=_model_info.get("input_cost_per_second", None), input_cost_per_audio_token=_model_info.get( @@ -5663,6 +5669,9 @@ def _get_model_info_helper( # noqa: PLR0915 output_cost_per_token_above_200k_tokens=_model_info.get( "output_cost_per_token_above_200k_tokens", None ), + output_cost_per_token_above_272k_tokens=_model_info.get( + "output_cost_per_token_above_272k_tokens", None + ), output_cost_per_second=_model_info.get("output_cost_per_second", None), output_cost_per_video_per_second=_model_info.get( "output_cost_per_video_per_second", None diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 4bc2c663811..f1ca7cd83b7 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -143,7 +143,7 @@ "notes": "DALL-E 2 via AI/ML API - Reliable text-to-image generation" }, "mode": "image_generation", - "output_cost_per_image": 0.021, + "output_cost_per_image": 0.026, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -155,7 +155,7 @@ "notes": "DALL-E 3 via AI/ML API - High-quality text-to-image generation" }, "mode": "image_generation", - "output_cost_per_image": 0.042, + "output_cost_per_image": 0.052, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -167,7 +167,7 @@ "notes": "Flux Dev - Development version optimized for experimentation" }, "mode": "image_generation", - "output_cost_per_image": 0.053, + "output_cost_per_image": 0.065, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -176,7 +176,7 @@ "aiml/flux-pro/v1.1": { "litellm_provider": "aiml", "mode": "image_generation", - "output_cost_per_image": 0.042, + "output_cost_per_image": 0.052, "supported_endpoints": [ "/v1/images/generations" ] @@ -195,7 +195,7 @@ "notes": "Flux Pro - Professional-grade image generation model" }, "mode": "image_generation", - "output_cost_per_image": 0.037, + "output_cost_per_image": 0.046, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -207,7 +207,7 @@ "notes": "Flux Dev - Development version optimized for experimentation" }, "mode": "image_generation", - "output_cost_per_image": 0.026, + "output_cost_per_image": 0.033, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -219,7 +219,7 @@ "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "mode": "image_generation", - "output_cost_per_image": 0.084, + "output_cost_per_image": 0.104, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -231,7 +231,7 @@ "notes": "Flux Pro v1.1 - Enhanced version with improved capabilities and 6x faster inference speed" }, "mode": "image_generation", - "output_cost_per_image": 0.042, + "output_cost_per_image": 0.052, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -243,7 +243,7 @@ "notes": "Flux Schnell - Fast generation model optimized for speed" }, "mode": "image_generation", - "output_cost_per_image": 0.003, + "output_cost_per_image": 0.004, "source": "https://docs.aimlapi.com/", "supported_endpoints": [ "/v1/images/generations" @@ -255,7 +255,7 @@ "notes": "Imagen 4.0 Ultra Generate API - Photorealistic image generation with precise text rendering" }, "mode": "image_generation", - "output_cost_per_image": 0.063, + "output_cost_per_image": 0.078, "source": "https://docs.aimlapi.com/api-references/image-models/google/imagen-4-ultra-generate", "supported_endpoints": [ "/v1/images/generations" @@ -267,7 +267,7 @@ "notes": "Gemini 3 Pro Image (Nano Banana Pro) - Advanced text-to-image generation with reasoning and 4K resolution support" }, "mode": "image_generation", - "output_cost_per_image": 0.1575, + "output_cost_per_image": 0.195, "source": "https://docs.aimlapi.com/api-references/image-models/google/gemini-3-pro-image-preview", "supported_endpoints": [ "/v1/images/generations" @@ -846,7 +846,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 3.125e-07 }, "anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, @@ -859,7 +861,9 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost": 1.875e-05 }, "anthropic.claude-3-sonnet-20240229-v1:0": { "input_cost_per_token": 3e-06, @@ -873,7 +877,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "anthropic.claude-instant-v1": { "input_cost_per_token": 8e-07, @@ -1233,7 +1239,7 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, - "apac.anthropic.claude-sonnet-4-6": { + "au.anthropic.claude-sonnet-4-6": { "cache_creation_input_token_cost": 4.125e-06, "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, "cache_read_input_token_cost": 3.3e-07, @@ -1512,7 +1518,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "apac.anthropic.claude-3-5-sonnet-20241022-v2:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -1545,7 +1553,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 3.125e-07 }, "apac.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -1581,7 +1591,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "apac.anthropic.claude-sonnet-4-20250514-v1:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -3040,6 +3052,37 @@ "supports_tool_choice": true, "supports_vision": false }, + "azure/gpt-audio-1.5-2026-02-23": { + "input_cost_per_audio_token": 4e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "azure", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 8e-05, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "azure/gpt-audio-mini-2025-10-06": { "input_cost_per_audio_token": 1e-05, "input_cost_per_token": 6e-07, @@ -3216,6 +3259,38 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "azure/gpt-realtime-1.5-2026-02-23": { + "cache_creation_input_audio_token_cost": 4e-06, + "cache_read_input_token_cost": 4e-06, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "azure", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "azure/gpt-realtime-mini-2025-10-06": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_token_cost": 6e-08, @@ -4124,6 +4199,36 @@ "supports_tool_choice": true, "supports_vision": true }, + "azure/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, + "litellm_provider": "azure", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.4e-05, + "supported_endpoints": [ + "/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 + }, "azure/gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, "litellm_provider": "azure", @@ -5712,6 +5817,15 @@ ], "source": "https://devblogs.microsoft.com/foundry/whats-new-in-azure-ai-foundry-august-2025/#mistral-document-ai-(ocr)-%E2%80%94-serverless-in-foundry" }, + "azure_ai/mistral-document-ai-2512": { + "litellm_provider": "azure_ai", + "ocr_cost_per_page": 0.003, + "mode": "ocr", + "supported_endpoints": [ + "/v1/ocr" + ], + "source": "https://azure.microsoft.com/en-us/pricing/details/ai-foundry-models/" + }, "azure_ai/doc-intelligence/prebuilt-read": { "litellm_provider": "azure_ai", "ocr_cost_per_page": 0.0015, @@ -6129,13 +6243,13 @@ "supports_tool_choice": true }, "azure_ai/mistral-small-2503": { - "input_cost_per_token": 1e-06, + "input_cost_per_token": 1e-07, "litellm_provider": "azure_ai", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 3e-07, "supports_function_calling": true, "supports_tool_choice": true, "supports_vision": true @@ -6832,7 +6946,9 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "bedrock/sa-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 4.45e-06, @@ -7251,7 +7367,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3.6e-07, + "cache_creation_input_token_cost": 4.5e-06 }, "bedrock/us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0": { "input_cost_per_token": 3e-07, @@ -7265,7 +7383,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07 }, "bedrock/us-gov-east-1/claude-sonnet-4-5-20250929-v1:0": { "input_cost_per_token": 3.3e-06, @@ -7283,7 +7403,9 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3.3e-07, + "cache_creation_input_token_cost": 4.125e-06 }, "bedrock/us-gov-east-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -7396,7 +7518,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3.6e-07, + "cache_creation_input_token_cost": 4.5e-06 }, "bedrock/us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0": { "input_cost_per_token": 3e-07, @@ -7410,7 +7534,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-08, + "cache_creation_input_token_cost": 3.75e-07 }, "bedrock/us-gov-west-1/claude-sonnet-4-5-20250929-v1:0": { "input_cost_per_token": 3.3e-06, @@ -7428,7 +7554,9 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3.3e-07, + "cache_creation_input_token_cost": 4.125e-06 }, "bedrock/us-gov-west-1/meta.llama3-70b-instruct-v1:0": { "input_cost_per_token": 2.65e-06, @@ -8295,37 +8423,6 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 346 }, - "us/claude-sonnet-4-6": { - "cache_creation_input_token_cost": 4.125e-06, - "cache_creation_input_token_cost_above_200k_tokens": 8.25e-06, - "cache_read_input_token_cost": 3.3e-07, - "cache_read_input_token_cost_above_200k_tokens": 6.6e-07, - "input_cost_per_token": 3.3e-06, - "input_cost_per_token_above_200k_tokens": 6.6e-06, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 64000, - "max_tokens": 64000, - "mode": "chat", - "output_cost_per_token": 1.65e-05, - "output_cost_per_token_above_200k_tokens": 2.475e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": true, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346, - "inference_geo": "us" - }, "claude-sonnet-4-5-20250929-v1:0": { "cache_creation_input_token_cost": 3.75e-06, "cache_read_input_token_cost": 3e-07, @@ -8517,100 +8614,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "fast/claude-opus-4-6": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_200k_tokens": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, - "input_cost_per_token": 3e-05, - "input_cost_per_token_above_200k_tokens": 1e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_above_200k_tokens": 3.75e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "us/claude-opus-4-6": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_200k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_1hr": 1.1e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1.1e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_200k_tokens": 1.1e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-05, - "output_cost_per_token_above_200k_tokens": 4.125e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "fast/us/claude-opus-4-6": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_200k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_1hr": 1.1e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1.1e-06, - "input_cost_per_token": 3e-05, - "input_cost_per_token_above_200k_tokens": 1.1e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_above_200k_tokens": 4.125e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "tool_use_system_prompt_tokens": 346, + "provider_specific_entry": { + "us": 1.1, + "fast": 6.0 + } }, "claude-opus-4-6-20260205": { "cache_creation_input_token_cost": 6.25e-06, @@ -8641,69 +8649,11 @@ "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "fast/claude-opus-4-6-20260205": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_200k_tokens": 1.25e-05, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1e-06, - "input_cost_per_token": 3e-05, - "input_cost_per_token_above_200k_tokens": 1e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 1000000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 0.00015, - "output_cost_per_token_above_200k_tokens": 3.75e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 - }, - "us/claude-opus-4-6-20260205": { - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_200k_tokens": 1.375e-05, - "cache_creation_input_token_cost_above_1hr": 1.1e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_200k_tokens": 1.1e-06, - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_200k_tokens": 1.1e-05, - "litellm_provider": "anthropic", - "max_input_tokens": 200000, - "max_output_tokens": 128000, - "max_tokens": 128000, - "mode": "chat", - "output_cost_per_token": 2.75e-05, - "output_cost_per_token_above_200k_tokens": 4.125e-05, - "search_context_cost_per_query": { - "search_context_size_high": 0.01, - "search_context_size_low": 0.01, - "search_context_size_medium": 0.01 - }, - "supports_assistant_prefill": false, - "supports_computer_use": true, - "supports_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_tool_choice": true, - "supports_vision": true, - "tool_use_system_prompt_tokens": 346 + "tool_use_system_prompt_tokens": 346, + "provider_specific_entry": { + "us": 1.1, + "fast": 6.0 + } }, "claude-sonnet-4-20250514": { "deprecation_date": "2026-05-14", @@ -9838,6 +9788,190 @@ } ] }, + "dashscope/qwen3-max-2026-01-23": { + "litellm_provider": "dashscope", + "max_input_tokens": 258048, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "tiered_pricing": [ + { + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 2.4e-06, + "output_cost_per_token": 1.2e-05, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "range": [ + 128000.0, + 252000.0 + ] + } + ] + }, + "dashscope/qwen3-next-80b-a3b-instruct": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_tool_choice": true + }, + "dashscope/qwen3-next-80b-a3b-thinking": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 262144, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "dashscope/qwen3-vl-235b-a22b-instruct": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 1.6e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen3-vl-235b-a22b-thinking": { + "input_cost_per_token": 4e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 4e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen3-vl-32b-instruct": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 6.4e-07, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen3-vl-32b-thinking": { + "input_cost_per_token": 1.6e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "output_cost_per_token": 2.87e-06, + "source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "dashscope/qwen3-vl-plus": { + "litellm_provider": "dashscope", + "max_input_tokens": 260096, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "input_cost_per_token": 2e-07, + "output_cost_per_token": 1.6e-06, + "range": [ + 0, + 32000.0 + ] + }, + { + "input_cost_per_token": 3e-07, + "output_cost_per_token": 2.4e-06, + "range": [ + 32000.0, + 128000.0 + ] + }, + { + "input_cost_per_token": 6e-07, + "output_cost_per_token": 4.8e-06, + "range": [ + 128000.0, + 256000.0 + ] + } + ] + }, + "dashscope/qwen3.5-plus": { + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "source": "https://www.alibabacloud.com/help/en/model-studio/models", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tiered_pricing": [ + { + "input_cost_per_token": 4e-07, + "output_cost_per_token": 2.4e-06, + "range": [ + 0, + 256000.0 + ] + }, + { + "input_cost_per_token": 5e-07, + "output_cost_per_token": 3e-06, + "range": [ + 256000.0, + 1000000.0 + ] + } + ] + }, "dashscope/qwq-plus": { "input_cost_per_token": 8e-07, "litellm_provider": "dashscope", @@ -10835,7 +10969,8 @@ "output_cost_per_token": 9e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B": { "max_tokens": 131072, @@ -10845,7 +10980,8 @@ "output_cost_per_token": 1e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B": { "max_tokens": 131072, @@ -10865,7 +11001,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen2.5-72B-Instruct": { "max_tokens": 32768, @@ -10875,7 +11012,8 @@ "output_cost_per_token": 3.9e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen2.5-7B-Instruct": { "max_tokens": 32768, @@ -10896,7 +11034,8 @@ "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-14B": { "max_tokens": 40960, @@ -10906,7 +11045,8 @@ "output_cost_per_token": 2.4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B": { "max_tokens": 40960, @@ -10916,7 +11056,8 @@ "output_cost_per_token": 5.4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507": { "max_tokens": 262144, @@ -10926,7 +11067,8 @@ "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507": { "max_tokens": 262144, @@ -10936,7 +11078,8 @@ "output_cost_per_token": 2.9e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-30B-A3B": { "max_tokens": 40960, @@ -10946,7 +11089,8 @@ "output_cost_per_token": 2.9e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-32B": { "max_tokens": 40960, @@ -10956,7 +11100,8 @@ "output_cost_per_token": 2.8e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct": { "max_tokens": 262144, @@ -10966,7 +11111,8 @@ "output_cost_per_token": 1.6e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo": { "max_tokens": 262144, @@ -10976,7 +11122,8 @@ "output_cost_per_token": 1.2e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct": { "max_tokens": 262144, @@ -10986,7 +11133,8 @@ "output_cost_per_token": 1.4e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking": { "max_tokens": 262144, @@ -10996,7 +11144,8 @@ "output_cost_per_token": 1.4e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo": { "max_tokens": 8192, @@ -11047,7 +11196,8 @@ "cache_read_input_token_cost": 3.3e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/anthropic/claude-4-opus": { "max_tokens": 200000, @@ -11057,7 +11207,8 @@ "output_cost_per_token": 8.25e-05, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/anthropic/claude-4-sonnet": { "max_tokens": 200000, @@ -11067,7 +11218,8 @@ "output_cost_per_token": 1.65e-05, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1": { "max_tokens": 163840, @@ -11077,7 +11229,8 @@ "output_cost_per_token": 2.4e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528": { "max_tokens": 163840, @@ -11088,7 +11241,8 @@ "cache_read_input_token_cost": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-0528-Turbo": { "max_tokens": 32768, @@ -11098,7 +11252,8 @@ "output_cost_per_token": 3e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { "max_tokens": 131072, @@ -11118,7 +11273,8 @@ "output_cost_per_token": 2.7e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-R1-Turbo": { "max_tokens": 40960, @@ -11128,7 +11284,8 @@ "output_cost_per_token": 3e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3": { "max_tokens": 163840, @@ -11138,7 +11295,8 @@ "output_cost_per_token": 8.9e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3-0324": { "max_tokens": 163840, @@ -11148,7 +11306,8 @@ "output_cost_per_token": 8.8e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3.1": { "max_tokens": 163840, @@ -11160,7 +11319,8 @@ "litellm_provider": "deepinfra", "mode": "chat", "supports_tool_choice": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true }, "deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus": { "max_tokens": 163840, @@ -11171,10 +11331,11 @@ "cache_read_input_token_cost": 2.16e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "max_tokens": 1000000, "max_input_tokens": 1000000, "max_output_tokens": 1000000, @@ -11182,7 +11343,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemini-2.5-flash": { "max_tokens": 1000000, @@ -11192,7 +11354,8 @@ "output_cost_per_token": 2.5e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemini-2.5-pro": { "max_tokens": 1000000, @@ -11202,7 +11365,8 @@ "output_cost_per_token": 1e-05, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemma-3-12b-it": { "max_tokens": 131072, @@ -11212,7 +11376,8 @@ "output_cost_per_token": 1e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemma-3-27b-it": { "max_tokens": 131072, @@ -11222,7 +11387,8 @@ "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/google/gemma-3-4b-it": { "max_tokens": 131072, @@ -11232,7 +11398,8 @@ "output_cost_per_token": 8e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.2-11B-Vision-Instruct": { "max_tokens": 131072, @@ -11252,7 +11419,8 @@ "output_cost_per_token": 2e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct": { "max_tokens": 131072, @@ -11262,7 +11430,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo": { "max_tokens": 131072, @@ -11272,6 +11441,7 @@ "output_cost_per_token": 3.9e-07, "litellm_provider": "deepinfra", "mode": "chat", + "supports_function_calling": true, "supports_tool_choice": true }, "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8": { @@ -11282,7 +11452,8 @@ "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct": { "max_tokens": 327680, @@ -11292,7 +11463,8 @@ "output_cost_per_token": 3e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Llama-Guard-3-8B": { "max_tokens": 131072, @@ -11322,7 +11494,8 @@ "output_cost_per_token": 6e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct": { "max_tokens": 131072, @@ -11332,7 +11505,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": { "max_tokens": 131072, @@ -11342,7 +11516,8 @@ "output_cost_per_token": 2.8e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct": { "max_tokens": 131072, @@ -11352,7 +11527,8 @@ "output_cost_per_token": 5e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo": { "max_tokens": 131072, @@ -11362,7 +11538,8 @@ "output_cost_per_token": 3e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/microsoft/WizardLM-2-8x22B": { "max_tokens": 65536, @@ -11382,7 +11559,8 @@ "output_cost_per_token": 1.4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Nemo-Instruct-2407": { "max_tokens": 131072, @@ -11392,7 +11570,8 @@ "output_cost_per_token": 4e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Small-24B-Instruct-2501": { "max_tokens": 32768, @@ -11402,7 +11581,8 @@ "output_cost_per_token": 8e-08, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506": { "max_tokens": 128000, @@ -11412,7 +11592,8 @@ "output_cost_per_token": 2e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1": { "max_tokens": 32768, @@ -11422,7 +11603,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct": { "max_tokens": 131072, @@ -11432,7 +11614,8 @@ "output_cost_per_token": 2e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/moonshotai/Kimi-K2-Instruct-0905": { "max_tokens": 262144, @@ -11443,7 +11626,8 @@ "cache_read_input_token_cost": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct": { "max_tokens": 131072, @@ -11453,7 +11637,8 @@ "output_cost_per_token": 6e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/nvidia/Llama-3.3-Nemotron-Super-49B-v1.5": { "max_tokens": 131072, @@ -11463,7 +11648,8 @@ "output_cost_per_token": 4e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": { "max_tokens": 131072, @@ -11473,7 +11659,8 @@ "output_cost_per_token": 1.6e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/openai/gpt-oss-120b": { "max_tokens": 131072, @@ -11483,7 +11670,8 @@ "output_cost_per_token": 4.5e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/openai/gpt-oss-20b": { "max_tokens": 131072, @@ -11493,7 +11681,8 @@ "output_cost_per_token": 1.5e-07, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepinfra/zai-org/GLM-4.5": { "max_tokens": 131072, @@ -11503,7 +11692,8 @@ "output_cost_per_token": 1.6e-06, "litellm_provider": "deepinfra", "mode": "chat", - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_function_calling": true }, "deepseek/deepseek-chat": { "cache_creation_input_token_cost": 0.0, @@ -12035,7 +12225,9 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 3.125e-07 }, "eu.anthropic.claude-haiku-4-5-20251001-v1:0": { "cache_creation_input_token_cost": 1.375e-06, @@ -12072,7 +12264,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-3-5-sonnet-20241022-v2:0": { "input_cost_per_token": 3e-06, @@ -12089,7 +12283,9 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-3-7-sonnet-20250219-v1:0": { "input_cost_per_token": 3e-06, @@ -12107,7 +12303,9 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-3-haiku-20240307-v1:0": { "input_cost_per_token": 2.5e-07, @@ -12121,7 +12319,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 3.125e-07 }, "eu.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, @@ -12134,7 +12334,9 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost": 1.875e-05 }, "eu.anthropic.claude-3-sonnet-20240229-v1:0": { "input_cost_per_token": 3e-06, @@ -12148,7 +12350,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "eu.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -13675,7 +13879,7 @@ }, "gemini-2.0-flash": { "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, "litellm_provider": "vertex_ai-language-models", @@ -13715,7 +13919,7 @@ }, "gemini-2.0-flash-001": { "cache_read_input_token_cost": 3.75e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1.5e-07, "litellm_provider": "vertex_ai-language-models", @@ -13801,7 +14005,7 @@ }, "gemini-2.0-flash-lite": { "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "vertex_ai-language-models", @@ -13837,7 +14041,7 @@ }, "gemini-2.0-flash-lite-001": { "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "vertex_ai-language-models", @@ -14279,6 +14483,89 @@ "supports_vision": true, "supports_web_search": true }, + "gemini-3.1-flash-image-preview": { + "input_cost_per_image": 0.00056, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0672, + "output_cost_per_image_token": 6e-05, + "output_cost_per_token": 3e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text", + "image" + ], + "supports_function_calling": false, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_vision": true, + "supports_web_search": true + }, + "gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "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_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true + }, "deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -14462,13 +14749,12 @@ "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" + "/vertex_ai/live" ], "supported_modalities": [ "text", @@ -14507,14 +14793,13 @@ "max_tokens": 65535, "max_video_length": 1, "max_videos_per_prompt": 10, - "mode": "chat", + "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, "output_cost_per_token": 2e-06, "rpm": 100000, "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions" + "/v1/realtime" ], "supported_modalities": [ "text", @@ -14722,6 +15007,7 @@ "supports_web_search": true }, "gemini-3-pro-preview": { + "deprecation_date": "2026-03-26", "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, @@ -14768,7 +15054,14 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, @@ -14819,7 +15112,14 @@ "supports_vision": true, "supports_web_search": true, "supports_url_context": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "gemini-3.1-pro-preview-customtools": { "cache_read_input_token_cost": 2e-07, @@ -14919,7 +15219,14 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "vertex_ai/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, @@ -14963,7 +15270,12 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 9e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "output_cost_per_token_priority": 5.4e-06, + "cache_read_input_token_cost_priority": 9e-08, + "supports_service_tier": true }, "vertex_ai/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, @@ -15014,7 +15326,14 @@ "supports_vision": true, "supports_web_search": true, "supports_url_context": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "vertex_ai/gemini-3.1-pro-preview-customtools": { "cache_read_input_token_cost": 2e-07, @@ -15065,7 +15384,14 @@ "supports_vision": true, "supports_web_search": true, "supports_url_context": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "gemini-2.5-pro-exp-03-25": { "cache_read_input_token_cost": 1.25e-07, @@ -15818,7 +16144,7 @@ }, "gemini/gemini-2.0-flash": { "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", @@ -15859,7 +16185,7 @@ }, "gemini/gemini-2.0-flash-001": { "cache_read_input_token_cost": 2.5e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, "litellm_provider": "gemini", @@ -15947,7 +16273,7 @@ }, "gemini/gemini-2.0-flash-lite": { "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "gemini", @@ -15983,7 +16309,7 @@ "tpm": 4000000 }, "gemini/gemini-2.0-flash-lite-preview-02-05": { - "deprecation_date": "2025-12-02", + "deprecation_date": "2025-12-09", "cache_read_input_token_cost": 1.875e-08, "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, @@ -16302,7 +16628,7 @@ "cache_read_input_token_cost": 3e-08, "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, - "litellm_provider": "vertex_ai-language-models", + "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, "supports_reasoning": false, @@ -16860,6 +17186,8 @@ "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, + "input_cost_per_token_priority": 1.25e-06, + "input_cost_per_token_above_200k_tokens_priority": 2.5e-06, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, @@ -16873,8 +17201,11 @@ "mode": "chat", "output_cost_per_token": 1e-05, "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token_priority": 1e-05, + "output_cost_per_token_above_200k_tokens_priority": 1.5e-05, "rpm": 2000, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "supports_service_tier": true, "supported_endpoints": [ "/v1/chat/completions", "/v1/completions" @@ -16933,6 +17264,7 @@ "tpm": 800000 }, "gemini/gemini-3-pro-preview": { + "deprecation_date": "2026-03-09", "cache_read_input_token_cost": 2e-07, "cache_read_input_token_cost_above_200k_tokens": 4e-07, "input_cost_per_token": 2e-06, @@ -16979,7 +17311,67 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": true, - "tpm": 800000 + "tpm": 800000, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true + }, + "gemini/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "gemini", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "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_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true, + "tpm": 250000 }, "gemini/gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, @@ -17027,7 +17419,12 @@ "supports_vision": true, "supports_web_search": true, "supports_native_streaming": true, - "tpm": 800000 + "tpm": 800000, + "input_cost_per_token_priority": 9e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "output_cost_per_token_priority": 5.4e-06, + "cache_read_input_token_cost_priority": 9e-08, + "supports_service_tier": true }, "gemini/gemini-3.1-pro-preview": { "cache_read_input_token_cost": 2e-07, @@ -17078,7 +17475,14 @@ "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, - "tpm": 800000 + "tpm": 800000, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "gemini/gemini-3.1-pro-preview-customtools": { "cache_read_input_token_cost": 2e-07, @@ -17129,7 +17533,14 @@ "supports_web_search": true, "supports_url_context": true, "supports_native_streaming": true, - "tpm": 800000 + "tpm": 800000, + "input_cost_per_token_priority": 3.6e-06, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "output_cost_per_token_priority": 2.16e-05, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "cache_read_input_token_cost_priority": 3.6e-07, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "supports_service_tier": true }, "gemini-3-flash-preview": { "cache_read_input_token_cost": 5e-08, @@ -17175,7 +17586,12 @@ "supports_url_context": true, "supports_vision": true, "supports_web_search": true, - "supports_native_streaming": true + "supports_native_streaming": true, + "input_cost_per_token_priority": 9e-07, + "input_cost_per_audio_token_priority": 1.8e-06, + "output_cost_per_token_priority": 5.4e-06, + "cache_read_input_token_cost_priority": 9e-08, + "supports_service_tier": true }, "gemini/gemini-2.5-pro-exp-03-25": { "cache_read_input_token_cost": 0.0, @@ -18021,6 +18437,93 @@ "max_tokens": 8191, "mode": "embedding" }, + "chatgpt/gpt-5.4": { + "litellm_provider": "chatgpt", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.4-pro": { + "litellm_provider": "chatgpt", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.3-codex": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.3-codex-spark": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "supported_endpoints": [ + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.3-instant": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, + "chatgpt/gpt-5.3-chat-latest": { + "litellm_provider": "chatgpt", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "responses", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_vision": true + }, "chatgpt/gpt-5.2-codex": { "litellm_provider": "chatgpt", "max_input_tokens": 128000, @@ -19187,6 +19690,39 @@ "supports_tool_choice": true, "supports_vision": false }, + "gpt-audio-1.5": { + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_token": 2.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1e-05, + "supported_endpoints": [ + "/v1/chat/completions" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_prompt_caching": false, + "supports_reasoning": false, + "supports_response_schema": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "gpt-audio-2025-08-28": { "input_cost_per_audio_token": 3.2e-05, "input_cost_per_token": 2.5e-06, @@ -20057,7 +20593,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5.1": { "cache_read_input_token_cost": 1.25e-07, @@ -20093,7 +20631,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": false }, "gpt-5.1-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -20129,7 +20669,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": false }, "gpt-5.1-chat-latest": { "cache_read_input_token_cost": 1.25e-07, @@ -20164,7 +20706,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": false }, "gpt-5.2": { "cache_read_input_token_cost": 1.75e-07, @@ -20201,7 +20745,10 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true }, "gpt-5.2-2025-12-11": { "cache_read_input_token_cost": 1.75e-07, @@ -20238,7 +20785,10 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_web_search": true }, "gpt-5.2-chat-latest": { "cache_read_input_token_cost": 1.75e-07, @@ -20272,7 +20822,47 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false, + "supports_web_search": true + }, + "gpt-5.3-chat-latest": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 128000, + "max_output_tokens": 16384, + "max_tokens": 16384, + "mode": "chat", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/v1/chat/completions", + "/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_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false, + "supports_web_search": true }, "gpt-5.2-pro": { "input_cost_per_token": 2.1e-05, @@ -20303,7 +20893,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true }, "gpt-5.2-pro-2025-12-11": { "input_cost_per_token": 2.1e-05, @@ -20334,20 +20926,72 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true }, "gpt-5.4": { "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, "cache_read_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, "input_cost_per_token_priority": 5e-06, + "input_cost_per_token_above_272k_tokens_priority": 1e-05, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, "output_cost_per_token_priority": 2.25e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.375e-05, + "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_service_tier": true, + "supports_vision": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true + }, + "gpt-5.4-2026-03-05": { + "cache_read_input_token_cost": 2.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 5e-07, + "cache_read_input_token_cost_priority": 5e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1e-06, + "input_cost_per_token": 2.5e-06, + "input_cost_per_token_above_272k_tokens": 5e-06, + "input_cost_per_token_priority": 5e-06, + "input_cost_per_token_above_272k_tokens_priority": 1e-05, + "litellm_provider": "openai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_272k_tokens": 2.25e-05, + "output_cost_per_token_priority": 2.25e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.375e-05, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -20372,18 +21016,24 @@ "supports_service_tier": true, "supports_vision": true }, - "gpt-5.4-2026-03-05": { - "cache_read_input_token_cost": 2.5e-07, - "cache_read_input_token_cost_priority": 5e-07, - "input_cost_per_token": 2.5e-06, - "input_cost_per_token_priority": 5e-06, + "gpt-5.4-pro": { + "cache_read_input_token_cost": 3e-06, + "cache_read_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost_priority": 6e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05, + "input_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_priority": 6e-05, + "input_cost_per_token_above_272k_tokens_priority": 1.2e-04, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", - "output_cost_per_token": 1.5e-05, - "output_cost_per_token_priority": 2.25e-05, + "output_cost_per_token": 1.8e-04, + "output_cost_per_token_above_272k_tokens": 2.7e-04, + "output_cost_per_token_priority": 2.7e-04, + "output_cost_per_token_above_272k_tokens_priority": 4.05e-04, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -20402,11 +21052,59 @@ "supports_pdf_input": true, "supports_prompt_caching": true, "supports_reasoning": true, - "supports_response_schema": true, + "supports_response_schema": false, "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true + }, + "gpt-5.4-pro-2026-03-05": { + "cache_read_input_token_cost": 3e-06, + "cache_read_input_token_cost_above_272k_tokens": 6e-06, + "cache_read_input_token_cost_priority": 6e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.2e-05, + "input_cost_per_token": 3e-05, + "input_cost_per_token_above_272k_tokens": 6e-05, + "input_cost_per_token_priority": 6e-05, + "input_cost_per_token_above_272k_tokens_priority": 1.2e-04, + "litellm_provider": "openai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.8e-04, + "output_cost_per_token_above_272k_tokens": 2.7e-04, + "output_cost_per_token_priority": 2.7e-04, + "output_cost_per_token_above_272k_tokens_priority": 4.05e-04, + "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": false, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_service_tier": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true }, "gpt-5-pro": { "input_cost_per_token": 1.5e-05, @@ -20439,7 +21137,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-pro-2025-10-06": { "input_cost_per_token": 1.5e-05, @@ -20472,7 +21172,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-2025-08-07": { "cache_read_input_token_cost": 1.25e-07, @@ -20511,7 +21213,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -20543,7 +21247,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-chat-latest": { "cache_read_input_token_cost": 1.25e-07, @@ -20575,7 +21281,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-codex": { "cache_read_input_token_cost": 1.25e-07, @@ -20605,7 +21313,9 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5.1-codex": { "cache_read_input_token_cost": 1.25e-07, @@ -20638,7 +21348,9 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5.1-codex-max": { "cache_read_input_token_cost": 1.25e-07, @@ -20668,7 +21380,9 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true }, "gpt-5.1-codex-mini": { "cache_read_input_token_cost": 2.5e-08, @@ -20701,7 +21415,9 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5.2-codex": { "cache_read_input_token_cost": 1.75e-07, @@ -20734,7 +21450,44 @@ "supports_response_schema": true, "supports_system_messages": false, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": true + }, + "gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "cache_read_input_token_cost_priority": 3.5e-07, + "input_cost_per_token": 1.75e-06, + "input_cost_per_token_priority": 3.5e-06, + "litellm_provider": "openai", + "max_input_tokens": 272000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "responses", + "output_cost_per_token": 1.4e-05, + "output_cost_per_token_priority": 2.8e-05, + "supported_endpoints": [ + "/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": false, + "supports_tool_choice": true, + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-mini": { "cache_read_input_token_cost": 2.5e-08, @@ -20773,7 +21526,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.5e-08, @@ -20812,7 +21567,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-nano": { "cache_read_input_token_cost": 5e-09, @@ -20848,7 +21605,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5e-09, @@ -20883,7 +21642,9 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-image-1": { "cache_read_input_image_token_cost": 2.5e-06, @@ -20943,6 +21704,38 @@ "supports_system_messages": true, "supports_tool_choice": true }, + "gpt-realtime-1.5": { + "cache_creation_input_audio_token_cost": 4e-07, + "cache_read_input_token_cost": 4e-07, + "input_cost_per_audio_token": 3.2e-05, + "input_cost_per_image": 5e-06, + "input_cost_per_token": 4e-06, + "litellm_provider": "openai", + "max_input_tokens": 32000, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_audio_token": 6.4e-05, + "output_cost_per_token": 1.6e-05, + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true + }, "gpt-realtime-mini": { "cache_creation_input_audio_token_cost": 3e-07, "cache_read_input_audio_token_cost": 3e-07, @@ -21412,6 +22205,21 @@ "supports_tool_choice": true, "supports_web_search": true }, + "groq/openai/gpt-oss-safeguard-20b": { + "cache_read_input_token_cost": 3.7e-08, + "input_cost_per_token": 7.5e-08, + "litellm_provider": "groq", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 3e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_web_search": true + }, "groq/playai-tts": { "input_cost_per_character": 5e-05, "litellm_provider": "groq", @@ -22727,6 +23535,19 @@ "max_input_tokens": 200000, "max_output_tokens": 8192 }, + "mistral.devstral-2-123b": { + "input_cost_per_token": 4e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 256000, + "max_output_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-06, + "supports_function_calling": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, "mistral.magistral-small-2509": { "input_cost_per_token": 5e-07, "litellm_provider": "bedrock_converse", @@ -23048,6 +23869,21 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/magistral-medium-1-2-2509": { + "input_cost_per_token": 2e-06, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://mistral.ai/news/magistral", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "mistral/mistral-ocr-latest": { "litellm_provider": "mistral", "ocr_cost_per_page": 0.001, @@ -23113,6 +23949,21 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/magistral-small-1-2-2509": { + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 40000, + "max_output_tokens": 40000, + "max_tokens": 40000, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://mistral.ai/pricing#api-pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "mistral/mistral-embed": { "input_cost_per_token": 1e-07, "litellm_provider": "mistral", @@ -23174,24 +24025,41 @@ "supports_tool_choice": true }, "mistral/mistral-large-latest": { - "input_cost_per_token": 2e-06, + "input_cost_per_token": 5e-07, "litellm_provider": "mistral", - "max_input_tokens": 128000, - "max_output_tokens": 128000, - "max_tokens": 128000, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 6e-06, + "output_cost_per_token": 1.5e-06, + "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true }, "mistral/mistral-large-3": { "input_cost_per_token": 5e-07, "litellm_provider": "mistral", - "max_input_tokens": 256000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-06, + "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-large-2512": { + "input_cost_per_token": 5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", "output_cost_per_token": 1.5e-06, "source": "https://docs.mistral.ai/models/mistral-large-3-25-12", @@ -23242,14 +24110,30 @@ "input_cost_per_token": 4e-07, "litellm_provider": "mistral", "max_input_tokens": 131072, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", "output_cost_per_token": 2e-06, "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-medium-3-1-2508": { + "input_cost_per_token": 4e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://mistral.ai/news/mistral-medium-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "mistral/mistral-small": { "input_cost_per_token": 1e-07, @@ -23265,17 +24149,79 @@ "supports_tool_choice": true }, "mistral/mistral-small-latest": { - "input_cost_per_token": 1e-07, + "input_cost_per_token": 6e-08, "litellm_provider": "mistral", - "max_input_tokens": 32000, - "max_output_tokens": 8191, - "max_tokens": 8191, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 3e-07, + "output_cost_per_token": 1.8e-07, + "source": "https://mistral.ai/pricing", "supports_assistant_prefill": true, "supports_function_calling": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/mistral-small-3-2-2506": { + "input_cost_per_token": 6e-08, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1.8e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-3-3b-2512": { + "input_cost_per_token": 1e-07, + "litellm_provider": "mistral", + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 1e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-3-8b-2512": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 1.5e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, + "mistral/ministral-3-14b-2512": { + "input_cost_per_token": 2e-07, + "litellm_provider": "mistral", + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "max_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://mistral.ai/pricing", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true }, "mistral/mistral-tiny": { "input_cost_per_token": 2.5e-07, @@ -23927,6 +24873,335 @@ "/v1/images/generations" ] }, + "nebius/deepseek-ai/DeepSeek-R1": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/deepseek-ai/DeepSeek-R1-0528": { + "max_tokens": 164000, + "max_input_tokens": 164000, + "max_output_tokens": 164000, + "input_cost_per_token": 8e-07, + "output_cost_per_token": 2.4e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2.5e-07, + "output_cost_per_token": 7.5e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/deepseek-ai/DeepSeek-V3": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/deepseek-ai/DeepSeek-V3-0324": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 1.5e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/google/gemma-3-27b-it": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Llama-3.3-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Llama-Guard-3-8B": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "nebius", + "mode": "chat", + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Meta-Llama-3.1-8B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Meta-Llama-3.1-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/meta-llama/Meta-Llama-3.1-405B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/mistralai/Mistral-Nemo-Instruct-2407": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 4e-08, + "output_cost_per_token": 1.2e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/NousResearch/Hermes-3-Llama-3.1-405B": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/nvidia/Llama-3.1-Nemotron-Ultra-253B-v1": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-07, + "output_cost_per_token": 1.8e-06, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/nvidia/Llama-3.3-Nemotron-Super-49B-v1": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen3-235B-A22B": { + "max_tokens": 262144, + "max_input_tokens": 262144, + "max_output_tokens": 262144, + "input_cost_per_token": 2e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen3-32B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen3-30B-A3B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-07, + "output_cost_per_token": 3e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen3-14B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen3-4B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 8e-08, + "output_cost_per_token": 2.4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/QwQ-32B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 4.5e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2.5-72B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2.5-32B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 2e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2.5-Coder-7B": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "max_output_tokens": 32768, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 3e-08, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2.5-VL-72B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2-VL-72B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 4e-07, + "litellm_provider": "nebius", + "mode": "chat", + "supports_function_calling": true, + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/Qwen/Qwen2-VL-7B-Instruct": { + "max_tokens": 131072, + "max_input_tokens": 131072, + "max_output_tokens": 131072, + "input_cost_per_token": 2e-08, + "output_cost_per_token": 6e-08, + "litellm_provider": "nebius", + "mode": "chat", + "supports_vision": true, + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/BAAI/bge-en-icl": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/BAAI/bge-multilingual-gemma2": { + "max_tokens": 8192, + "max_input_tokens": 8192, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://nebius.com/prices-ai-studio" + }, + "nebius/intfloat/e5-mistral-7b-instruct": { + "max_tokens": 32768, + "max_input_tokens": 32768, + "input_cost_per_token": 1e-08, + "output_cost_per_token": 0.0, + "litellm_provider": "nebius", + "mode": "embedding", + "source": "https://nebius.com/prices-ai-studio" + }, "nvidia.nemotron-nano-12b-v2": { "input_cost_per_token": 2e-07, "litellm_provider": "bedrock_converse", @@ -25074,6 +26349,30 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, + "openrouter/anthropic/claude-sonnet-4.6": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, + "cache_read_input_token_cost": 3e-07, + "cache_read_input_token_cost_above_200k_tokens": 6e-07, + "input_cost_per_token": 3e-06, + "input_cost_per_token_above_200k_tokens": 6e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.5e-05, + "output_cost_per_token_above_200k_tokens": 2.25e-05, + "source": "https://openrouter.ai/anthropic/claude-sonnet-4.6", + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 159 + }, "openrouter/anthropic/claude-opus-4.5": { "cache_creation_input_token_cost": 6.25e-06, "cache_read_input_token_cost": 5e-07, @@ -25093,6 +26392,25 @@ "supports_vision": true, "tool_use_system_prompt_tokens": 159 }, + "openrouter/anthropic/claude-opus-4.6": { + "cache_creation_input_token_cost": 6.25e-06, + "cache_read_input_token_cost": 5e-07, + "input_cost_per_token": 5e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.5e-05, + "supports_assistant_prefill": true, + "supports_computer_use": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true, + "tool_use_system_prompt_tokens": 346 + }, "openrouter/anthropic/claude-sonnet-4.5": { "input_cost_per_image": 0.0048, "cache_creation_input_token_cost": 3.75e-06, @@ -25245,7 +26563,7 @@ "supports_tool_choice": true }, "openrouter/google/gemini-2.0-flash-001": { - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7e-07, "input_cost_per_token": 1e-07, "litellm_provider": "openrouter", @@ -25405,6 +26723,39 @@ "supports_web_search": true, "tpm": 800000 }, + "openrouter/google/gemini-3.1-pro-preview": { + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, + "source": "https://openrouter.ai/google/gemini-3.1-pro-preview", + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_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 + }, "openrouter/gryphe/mythomax-l2-13b": { "input_cost_per_token": 1.875e-06, "litellm_provider": "openrouter", @@ -25782,6 +27133,29 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "openrouter/openai/gpt-5.1-codex-max": { + "cache_read_input_token_cost": 1.25e-07, + "input_cost_per_token": 1.25e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 400000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "source": "https://openrouter.ai/openai/gpt-5.1-codex-max", + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "supports_vision": true + }, "openrouter/openai/gpt-5.2": { "input_cost_per_image": 0, "cache_read_input_token_cost": 1.75e-07, @@ -25936,6 +27310,19 @@ "supports_tool_choice": true, "supports_function_calling": true }, + "openrouter/qwen/qwen3-coder-plus": { + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 997952, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/qwen/qwen3-coder-plus", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "openrouter/qwen/qwen3-235b-a22b-2507": { "input_cost_per_token": 7.1e-08, "litellm_provider": "openrouter", @@ -26071,6 +27458,19 @@ "supports_vision": true, "supports_prompt_caching": false }, + "openrouter/z-ai/glm-5": { + "input_cost_per_token": 8e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 202752, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2.56e-06, + "source": "https://openrouter.ai/z-ai/glm-5", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, "openrouter/minimax/minimax-m2.1": { "input_cost_per_token": 2.7e-07, "output_cost_per_token": 1.2e-06, @@ -26105,6 +27505,42 @@ "supports_prompt_caching": true, "supports_computer_use": false }, + "openrouter/openrouter/auto": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 2000000, + "max_tokens": 2000000, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true, + "supports_audio_input": true, + "supports_video_input": true + }, + "openrouter/openrouter/free": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_vision": true + }, + "openrouter/openrouter/bodybuilder": { + "input_cost_per_token": 0, + "output_cost_per_token": 0, + "litellm_provider": "openrouter", + "max_input_tokens": 128000, + "max_tokens": 128000, + "mode": "chat" + }, "ovhcloud/DeepSeek-R1-Distill-Llama-70B": { "input_cost_per_token": 6.7e-07, "litellm_provider": "ovhcloud", @@ -26651,8 +28087,8 @@ "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", - "supports_function_calling": true, - "supports_tool_choice": true + "supports_function_calling": false, + "supports_tool_choice": false }, "publicai/swiss-ai/apertus-70b-instruct": { "input_cost_per_token": 0.0, @@ -26663,8 +28099,8 @@ "mode": "chat", "output_cost_per_token": 0.0, "source": "https://platform.publicai.co/docs", - "supports_function_calling": true, - "supports_tool_choice": true + "supports_function_calling": false, + "supports_tool_choice": false }, "publicai/aisingapore/Gemma-SEA-LION-v4-27B-IT": { "input_cost_per_token": 0.0, @@ -26714,65 +28150,144 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "perplexity/preset/fast-search": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_preset": true, + "supports_function_calling": true + }, "perplexity/preset/pro-search": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_preset": true + "supports_preset": true, + "supports_function_calling": true }, - "perplexity/openai/gpt-4o": { + "perplexity/preset/deep-research": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_preset": true, + "supports_function_calling": true }, - "perplexity/openai/gpt-4o-mini": { + "perplexity/preset/advanced-deep-research": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_preset": true, + "supports_function_calling": true }, "perplexity/openai/gpt-5.2": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_function_calling": true }, - "perplexity/anthropic/claude-3-5-sonnet-20241022": { + "perplexity/openai/gpt-5.1": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_reasoning": false, + "supports_function_calling": true }, - "perplexity/anthropic/claude-3-5-haiku-20241022": { + "perplexity/openai/gpt-5-mini": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_reasoning": false, + "supports_function_calling": true }, - "perplexity/google/gemini-2.0-flash-exp": { + "perplexity/anthropic/claude-opus-4-6": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_reasoning": false, + "supports_function_calling": true }, - "perplexity/google/gemini-2.0-flash-thinking-exp": { + "perplexity/anthropic/claude-opus-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": true + "supports_reasoning": false, + "supports_function_calling": true }, - "perplexity/xai/grok-2-1212": { + "perplexity/anthropic/claude-sonnet-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_reasoning": false, + "supports_function_calling": true }, - "perplexity/xai/grok-2-vision-1212": { + "perplexity/anthropic/claude-haiku-4-5": { "litellm_provider": "perplexity", "mode": "responses", "supports_web_search": true, - "supports_reasoning": false + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/google/gemini-3-pro-preview": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/google/gemini-3-flash-preview": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/google/gemini-2.5-pro": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/google/gemini-2.5-flash": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/xai/grok-4-1-fast-non-reasoning": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/perplexity/sonar": { + "litellm_provider": "perplexity", + "mode": "responses", + "supports_web_search": true, + "supports_reasoning": false, + "supports_function_calling": true + }, + "perplexity/pplx-embed-v1-0.6b": { + "input_cost_per_token": 4e-09, + "litellm_provider": "perplexity", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 1024, + "source": "https://docs.perplexity.ai/docs/embeddings/quickstart" + }, + "perplexity/pplx-embed-v1-4b": { + "input_cost_per_token": 3e-08, + "litellm_provider": "perplexity", + "max_input_tokens": 32768, + "max_tokens": 32768, + "mode": "embedding", + "output_cost_per_token": 0.0, + "output_vector_size": 2560, + "source": "https://docs.perplexity.ai/docs/embeddings/quickstart" }, "publicai/aisingapore/Qwen-SEA-LION-v4-32B-IT": { "input_cost_per_token": 0.0, @@ -28870,6 +30385,18 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/Qwen/Qwen3.5-397B-A17B": { + "input_cost_per_token": 6e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 262144, + "mode": "chat", + "output_cost_per_token": 3.6e-06, + "source": "https://www.together.ai/models/Qwen/Qwen3.5-397B-A17B", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "tts-1": { "input_cost_per_character": 1.5e-05, "litellm_provider": "openai", @@ -29027,7 +30554,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "us.anthropic.claude-3-5-sonnet-20241022-v2:0": { "cache_creation_input_token_cost": 3.75e-06, @@ -29080,7 +30609,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 2.5e-08, + "cache_creation_input_token_cost": 3.125e-07 }, "us.anthropic.claude-3-opus-20240229-v1:0": { "input_cost_per_token": 1.5e-05, @@ -29093,7 +30624,9 @@ "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 1.5e-06, + "cache_creation_input_token_cost": 1.875e-05 }, "us.anthropic.claude-3-sonnet-20240229-v1:0": { "input_cost_per_token": 3e-06, @@ -29107,7 +30640,9 @@ "supports_pdf_input": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 3e-07, + "cache_creation_input_token_cost": 3.75e-06 }, "us.anthropic.claude-opus-4-1-20250805-v1:0": { "cache_creation_input_token_cost": 1.875e-05, @@ -30000,7 +31535,7 @@ "supports_tool_choice": true }, "vercel_ai_gateway/google/gemini-2.0-flash": { - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_token": 1.5e-07, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, @@ -30014,7 +31549,7 @@ "supports_response_schema": true }, "vercel_ai_gateway/google/gemini-2.0-flash-lite": { - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_token": 7.5e-08, "litellm_provider": "vercel_ai_gateway", "max_input_tokens": 1048576, @@ -31519,6 +33054,70 @@ "output_cost_per_token_batches": 6e-06, "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image" }, + "vertex_ai/gemini-3.1-flash-image-preview": { + "input_cost_per_image": 0.00056, + "input_cost_per_token": 5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_input_tokens": 65536, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "image_generation", + "output_cost_per_image": 0.0672, + "output_cost_per_image_token": 6e-05, + "output_cost_per_token": 3e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models" + }, + "vertex_ai/gemini-3.1-flash-lite-preview": { + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "litellm_provider": "vertex_ai-language-models", + "max_audio_length_hours": 8.4, + "max_audio_per_prompt": 1, + "max_images_per_prompt": 3000, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_pdf_size_mb": 30, + "max_tokens": 65536, + "max_video_length": 1, + "max_videos_per_prompt": 10, + "mode": "chat", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_input": true, + "supports_audio_output": false, + "supports_code_execution": true, + "supports_file_search": true, + "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_video_input": true, + "supports_vision": true, + "supports_web_search": true, + "supports_native_streaming": true + }, "vertex_ai/deep-research-pro-preview-12-2025": { "input_cost_per_image": 0.0011, "input_cost_per_token": 2e-06, @@ -32920,6 +34519,7 @@ "supports_web_search": true }, "xai/grok-2-vision-1212": { + "deprecation_date": "2026-02-28", "input_cost_per_image": 2e-06, "input_cost_per_token": 2e-06, "litellm_provider": "xai", @@ -33024,6 +34624,7 @@ }, "xai/grok-3-mini": { "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-02-28", "input_cost_per_token": 3e-07, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33040,6 +34641,7 @@ }, "xai/grok-3-mini-beta": { "cache_read_input_token_cost": 7.5e-08, + "deprecation_date": "2026-02-28", "input_cost_per_token": 3e-07, "litellm_provider": "xai", "max_input_tokens": 131072, @@ -33374,6 +34976,50 @@ "supports_tool_choice": true, "source": "https://aws.amazon.com/bedrock/pricing/" }, + "zai.glm-4.7-flash": { + "input_cost_per_token": 7e-08, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 4e-07, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "source": "https://aws.amazon.com/bedrock/pricing/" + }, + "zai/glm-5": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 1e-06, + "output_cost_per_token": 3.2e-06, + "litellm_provider": "zai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "mode": "chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing" + }, + "zai/glm-5-code": { + "cache_creation_input_token_cost": 0, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 1.2e-06, + "output_cost_per_token": 5e-06, + "litellm_provider": "zai", + "max_input_tokens": 200000, + "max_output_tokens": 128000, + "mode": "chat", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": true, + "source": "https://docs.z.ai/guides/overview/pricing" + }, "zai/glm-4.7": { "cache_creation_input_token_cost": 0, "cache_read_input_token_cost": 1.1e-07, @@ -37158,7 +38804,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-5-search-api-2025-10-14": { "cache_read_input_token_cost": 1.25e-07, @@ -37177,7 +38825,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "supports_none_reasoning_effort": false, + "supports_xhigh_reasoning_effort": false }, "gpt-realtime-mini-2025-10-06": { "cache_creation_input_audio_token_cost": 3e-07, @@ -37355,7 +39005,7 @@ }, "gemini/gemini-2.0-flash-lite-001": { "cache_read_input_token_cost": 1.875e-08, - "deprecation_date": "2026-03-31", + "deprecation_date": "2026-06-01", "input_cost_per_audio_token": 7.5e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "gemini", @@ -37820,5 +39470,59 @@ "metadata": { "notes": "DuckDuckGo Instant Answer API is free and does not require an API key." } + }, + "bedrock_mantle/openai.gpt-oss-120b": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/openai.gpt-oss-20b": { + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 3e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 32768, + "max_tokens": 32768, + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/openai.gpt-oss-safeguard-120b": { + "input_cost_per_token": 1.5e-07, + "output_cost_per_token": 6e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "bedrock_mantle/openai.gpt-oss-safeguard-20b": { + "input_cost_per_token": 7.5e-08, + "output_cost_per_token": 3e-07, + "litellm_provider": "bedrock_mantle", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true } } diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index b45cbbd99c0..4f43028d025 100644 --- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -23,8 +23,8 @@ sys.path.insert( ) # Adds the parent directory to the system path from litellm.litellm_core_utils.llm_cost_calc.utils import ( - _calculate_input_cost, PromptTokensDetailsResult, + _calculate_input_cost, calculate_cache_writing_cost, generic_cost_per_token, ) @@ -239,6 +239,32 @@ def test_generic_cost_per_token_above_200k_tokens(): ) +def test_generic_cost_per_token_gpt54_above_272k_tokens(): + """GPT-5.4/5.4-pro: prompts >272K input tokens priced at 2x input, 1.5x output.""" + model = "gpt-5.4" + custom_llm_provider = "openai" + os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True" + litellm.model_cost = litellm.get_model_cost_map(url="") + + model_cost_map = litellm.model_cost[model] + prompt_tokens = 273000 # Above 272K threshold + completion_tokens = 1000 + usage = Usage( + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + total_tokens=prompt_tokens + completion_tokens, + ) + prompt_cost, completion_cost = generic_cost_per_token( + model=model, + usage=usage, + custom_llm_provider=custom_llm_provider, + ) + expected_prompt = model_cost_map["input_cost_per_token_above_272k_tokens"] * prompt_tokens + expected_completion = model_cost_map["output_cost_per_token_above_272k_tokens"] * completion_tokens + assert round(prompt_cost, 10) == round(expected_prompt, 10) + assert round(completion_cost, 10) == round(expected_completion, 10) + + def test_generic_cost_per_token_anthropic_prompt_caching(): model = "claude-sonnet-4@20250514" usage = Usage( diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index 3ae45882780..70818af547f 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -13,12 +13,12 @@ sys.path.insert( import litellm from litellm.proxy.utils import is_valid_api_key from litellm.types.utils import ( + CallTypes, Delta, LlmProviders, ModelResponseStream, StreamingChoices, ) -from litellm.types.utils import CallTypes from litellm.utils import ( ProviderConfigManager, TextCompletionStreamWrapper, @@ -96,6 +96,19 @@ def test_supports_function_calling_github_anthropic_alias(): ) +def test_supports_function_calling_deepinfra_llama(): + """Test that deepinfra Llama models correctly report function calling support. + + Regression test for https://github.com/BerriAI/litellm/issues/22619 + """ + assert ( + litellm.utils.supports_function_calling( + model="deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo" + ) + is True + ) + + def test_supports_function_calling_unknown_github_alias_returns_false(): assert ( litellm.utils.supports_function_calling( @@ -500,6 +513,8 @@ def validate_model_cost_values(model_data, exceptions=None): "output_cost_per_token_above_128k_tokens", "input_cost_per_token_above_200k_tokens", "output_cost_per_token_above_200k_tokens", + "input_cost_per_token_above_272k_tokens", + "output_cost_per_token_above_272k_tokens", "input_cost_per_character_above_128k_tokens", "output_cost_per_character_above_128k_tokens", "input_cost_per_image_above_128k_tokens", @@ -590,8 +605,10 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "cache_creation_input_token_cost_above_200k_tokens": {"type": "number"}, "cache_read_input_token_cost": {"type": "number"}, "cache_read_input_token_cost_above_200k_tokens": {"type": "number"}, + "cache_read_input_token_cost_above_272k_tokens": {"type": "number"}, "cache_creation_input_token_cost_above_1hr_above_200k_tokens": {"type": "number"}, "cache_read_input_audio_token_cost": {"type": "number"}, + "cache_read_input_token_cost_per_audio_token": {"type": "number"}, "cache_read_input_image_token_cost": {"type": "number"}, "deprecation_date": {"type": "string"}, "input_cost_per_audio_per_second": {"type": "number"}, @@ -604,12 +621,20 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "input_cost_per_image_above_128k_tokens": {"type": "number"}, "input_cost_per_image_token": {"type": "number"}, "input_cost_per_token_above_200k_tokens": {"type": "number"}, + "input_cost_per_token_above_272k_tokens": {"type": "number"}, "cache_read_input_token_cost_flex": {"type": "number"}, "cache_read_input_token_cost_priority": {"type": "number"}, + "cache_read_input_token_cost_above_200k_tokens_priority": {"type": "number"}, + "cache_read_input_token_cost_above_272k_tokens_priority": {"type": "number"}, "input_cost_per_token_flex": {"type": "number"}, "input_cost_per_token_priority": {"type": "number"}, + "input_cost_per_token_above_200k_tokens_priority": {"type": "number"}, + "input_cost_per_token_above_272k_tokens_priority": {"type": "number"}, + "input_cost_per_audio_token_priority": {"type": "number"}, "output_cost_per_token_flex": {"type": "number"}, "output_cost_per_token_priority": {"type": "number"}, + "output_cost_per_token_above_200k_tokens_priority": {"type": "number"}, + "output_cost_per_token_above_272k_tokens_priority": {"type": "number"}, "input_cost_per_pixel": {"type": "number"}, "input_cost_per_query": {"type": "number"}, "input_cost_per_request": {"type": "number"}, @@ -644,6 +669,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "max_video_length": {"type": "number"}, "max_videos_per_prompt": {"type": "number"}, "metadata": {"type": "object"}, + "provider_specific_entry": {"type": "object"}, "mode": { "type": "string", "enum": [ @@ -658,6 +684,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "video_generation", "moderation", "rerank", + "realtime", "responses", "ocr", "search", @@ -674,6 +701,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "output_cost_per_token": {"type": "number"}, "output_cost_per_token_above_128k_tokens": {"type": "number"}, "output_cost_per_token_above_200k_tokens": {"type": "number"}, + "output_cost_per_token_above_272k_tokens": {"type": "number"}, "output_cost_per_image_above_1024_and_1024_pixels": {"type": "number"}, "output_cost_per_image_above_1024_and_1024_pixels_and_premium_image": { "type": "number" @@ -697,6 +725,8 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "supports_audio_input": {"type": "boolean"}, "supports_audio_output": {"type": "boolean"}, "supports_embedding_image_input": {"type": "boolean"}, + "supports_code_execution": {"type": "boolean"}, + "supports_file_search": {"type": "boolean"}, "supports_function_calling": {"type": "boolean"}, "supports_image_input": {"type": "boolean"}, "supports_parallel_function_calling": {"type": "boolean"}, @@ -710,10 +740,13 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "supports_web_search": {"type": "boolean"}, "supports_url_context": {"type": "boolean"}, "supports_reasoning": {"type": "boolean"}, + "supports_none_reasoning_effort": {"type": "boolean"}, + "supports_xhigh_reasoning_effort": {"type": "boolean"}, "supports_service_tier": {"type": "boolean"}, "supports_preset": {"type": "boolean"}, "tool_use_system_prompt_tokens": {"type": "number"}, "tpm": {"type": "number"}, + "provider_specific_entry": {"type": "object"}, "supported_endpoints": { "type": "array", "items": { @@ -802,8 +835,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): }, } - prod_json = "./model_prices_and_context_window.json" - # prod_json = "../../model_prices_and_context_window.json" + prod_json = os.path.join(os.path.dirname(__file__), "..", "..", "model_prices_and_context_window.json") with open(prod_json, "r") as model_prices_file: actual_json = json.load(model_prices_file) assert isinstance(actual_json, dict) @@ -1134,20 +1166,25 @@ def test_pre_process_non_default_params(model, custom_llm_provider): provider_config=provider_config, ) print(processed_non_default_params) + # Vertex AI / Gemini uses Pydantic's model_json_schema() which doesn't + # include additionalProperties: False (Gemini rejects it). Other + # providers use OpenAI's to_strict_json_schema() which does. + expected_schema = { + "properties": { + "x": {"title": "X", "type": "string"}, + "y": {"title": "Y", "type": "string"}, + }, + "required": ["x", "y"], + "title": "ResponseFormat", + "type": "object", + } + if custom_llm_provider not in ("vertex_ai", "vertex_ai_beta", "gemini"): + expected_schema["additionalProperties"] = False assert processed_non_default_params == { "response_format": { "type": "json_schema", "json_schema": { - "schema": { - "properties": { - "x": {"title": "X", "type": "string"}, - "y": {"title": "Y", "type": "string"}, - }, - "required": ["x", "y"], - "title": "ResponseFormat", - "type": "object", - "additionalProperties": False, - }, + "schema": expected_schema, "name": "ResponseFormat", "strict": True, }, @@ -2337,7 +2374,7 @@ def test_register_model_with_scientific_notation(): Test that the register_model function can handle scientific notation in the model name. """ import uuid - + # Use a truly unique model name with uuid to avoid conflicts when tests run in parallel test_model_name = f"test-scientific-notation-model-{uuid.uuid4().hex[:12]}" @@ -2372,6 +2409,64 @@ def test_register_model_with_scientific_notation(): _invalidate_model_cost_lowercase_map() +def test_register_model_openrouter_without_slash(): + """ + Test that register_model handles openrouter models without '/' in the name. + + Fixes https://github.com/BerriAI/litellm/issues/18936 + + Previously, the code did `split_string[1]` which would fail with IndexError + when the model name didn't contain '/'. Now it uses `split_string[-1]` which + always works. + """ + # Clear any existing entries + litellm.openrouter_models.discard("my-custom-alias") + litellm.openrouter_models.discard("gpt-4") + litellm.openrouter_models.discard("openai/gpt-4") + + # Test 1: Model name without '/' (this was the bug - would raise IndexError) + litellm.register_model( + { + "my-custom-alias": { + "max_tokens": 8192, + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00002, + "litellm_provider": "openrouter", + "mode": "chat", + }, + } + ) + assert "my-custom-alias" in litellm.openrouter_models + + # Test 2: Model name with single '/' (openrouter/model format) + litellm.register_model( + { + "openrouter/gpt-4": { + "max_tokens": 8192, + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00002, + "litellm_provider": "openrouter", + "mode": "chat", + }, + } + ) + assert "gpt-4" in litellm.openrouter_models + + # Test 3: Model name with double '/' (openrouter/provider/model format) + litellm.register_model( + { + "openrouter/openai/gpt-4-turbo": { + "max_tokens": 8192, + "input_cost_per_token": 0.00001, + "output_cost_per_token": 0.00002, + "litellm_provider": "openrouter", + "mode": "chat", + }, + } + ) + assert "openai/gpt-4-turbo" in litellm.openrouter_models + + def test_reasoning_content_preserved_in_text_completion_wrapper(): """Ensure reasoning_content is copied from delta to text_choices.""" chunk = ModelResponseStream( @@ -2981,8 +3076,8 @@ class TestProxyLoggingBudgetAlerts: via metadata.soft_budget_alerting_emails to work even when global alerting is disabled. """ from litellm.caching.caching import DualCache - from litellm.proxy.utils import ProxyLogging from litellm.proxy._types import CallInfo, Litellm_EntityType + from litellm.proxy.utils import ProxyLogging proxy_logging = ProxyLogging(user_api_key_cache=DualCache()) proxy_logging.alerting = None # Global alerting is disabled @@ -3018,8 +3113,8 @@ class TestProxyLoggingBudgetAlerts: and do not send emails when alerting is None. """ from litellm.caching.caching import DualCache - from litellm.proxy.utils import ProxyLogging from litellm.proxy._types import CallInfo, Litellm_EntityType + from litellm.proxy.utils import ProxyLogging proxy_logging = ProxyLogging(user_api_key_cache=DualCache()) proxy_logging.alerting = None @@ -3050,8 +3145,8 @@ class TestProxyLoggingBudgetAlerts: Test that soft_budget alerts with empty alert_emails list still respect alerting=None. """ from litellm.caching.caching import DualCache - from litellm.proxy.utils import ProxyLogging from litellm.proxy._types import CallInfo, Litellm_EntityType + from litellm.proxy.utils import ProxyLogging proxy_logging = ProxyLogging(user_api_key_cache=DualCache()) proxy_logging.alerting = None @@ -3554,3 +3649,43 @@ class TestMetadataNoneHandling: litellm_params = {"metadata": None} metadata = litellm_params.get("metadata") or {} assert metadata == {} + + +class TestValidateAndFixThinkingParam: + """Tests for validate_and_fix_thinking_param.""" + + def test_none_returns_none(self): + from litellm.utils import validate_and_fix_thinking_param + + assert validate_and_fix_thinking_param(thinking=None) is None + + def test_already_snake_case(self): + from litellm.utils import validate_and_fix_thinking_param + + thinking = {"type": "enabled", "budget_tokens": 32000} + result = validate_and_fix_thinking_param(thinking=thinking) + assert result == {"type": "enabled", "budget_tokens": 32000} + + def test_camel_case_normalized(self): + from litellm.utils import validate_and_fix_thinking_param + + thinking = {"type": "enabled", "budgetTokens": 32000} + result = validate_and_fix_thinking_param(thinking=thinking) + assert result == {"type": "enabled", "budget_tokens": 32000} + assert "budgetTokens" not in result + + def test_both_keys_snake_case_wins(self): + from litellm.utils import validate_and_fix_thinking_param + + thinking = {"type": "enabled", "budget_tokens": 10000, "budgetTokens": 50000} + result = validate_and_fix_thinking_param(thinking=thinking) + assert result == {"type": "enabled", "budget_tokens": 10000} + assert "budgetTokens" not in result + + def test_original_dict_not_mutated(self): + from litellm.utils import validate_and_fix_thinking_param + + thinking = {"type": "enabled", "budgetTokens": 32000} + validate_and_fix_thinking_param(thinking=thinking) + assert "budgetTokens" in thinking + assert "budget_tokens" not in thinking