diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index c147f4bf94b..81c0c045a30 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -12260,7 +12260,7 @@ "azure_ai/deepseek-v3.2": { "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 163840, + "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12368,7 +12368,7 @@ "azure_ai/grok-4": { "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, + "max_input_tokens": 262000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -12490,7 +12490,7 @@ "azure_ai/grok-code-fast-1": { "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, + "max_input_tokens": 256000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -27518,7 +27518,8 @@ "search_context_size_high": 0.035 }, "gemini_native_audio": true, - "input_cost_per_image_token": 3e-06 + "input_cost_per_image_token": 3e-06, + "input_cost_per_video_token": 3e-06 }, "gemini-live-2.5-flash-preview-native-audio-09-2025": { "input_cost_per_audio_token": 3e-06, @@ -28418,7 +28419,7 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "search_context_cost_per_query": { @@ -29015,7 +29016,7 @@ "image" ], "supports_function_calling": false, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, @@ -29026,7 +29027,7 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "supports_reasoning": false + "supports_reasoning": true }, "gemini/nano-banana-pro-preview": { "input_cost_per_image": 0.0011, @@ -29104,8 +29105,8 @@ "image" ], "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, @@ -29115,7 +29116,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "supports_pdf_input": true }, "gemini/gemini-3.1-flash-lite-image": { "input_cost_per_image": 0.00028, @@ -29146,8 +29148,9 @@ "image" ], "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, @@ -29159,17 +29162,15 @@ "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -29177,11 +29178,12 @@ ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": false, "supports_prompt_caching": true, @@ -29193,7 +29195,8 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_pdf_input": true }, "gemini/gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, @@ -30785,11 +30788,15 @@ ] }, "github_copilot/claude-haiku-4.5": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 5e-06, "supported_endpoints": [ "/v1/chat/completions" ], @@ -30838,11 +30845,15 @@ "supports_vision": true }, "github_copilot/claude-sonnet-4": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 1.5e-05, "supported_endpoints": [ "/v1/chat/completions" ], @@ -31003,11 +31014,14 @@ "supports_vision": true }, "github_copilot/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -31058,11 +31072,14 @@ "supports_vision": true }, "github_copilot/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1.4e-05, "supported_endpoints": [ "/v1/responses" ], @@ -32745,6 +32762,25 @@ "audio" ] }, + "gpt-4o-mini-tts-2025-03-20": { + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] + }, "gpt-4o-search-preview": { "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, @@ -42065,8 +42101,8 @@ "input_cost_per_token_cache_hit": 2e-08, "litellm_provider": "openrouter", "max_input_tokens": 163840, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 147456, + "max_tokens": 147456, "mode": "chat", "output_cost_per_token": 4.1e-07, "source": "https://openrouter.ai/api/v1/models", @@ -42146,14 +42182,14 @@ "supports_web_search": false }, "openrouter/deepseek/deepseek-v4.1-flash": { - "cache_read_input_token_cost": 3.135e-08, - "input_cost_per_token": 3.483e-08, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 1.2e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -42173,7 +42209,7 @@ "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 3.5e-06, + "output_cost_per_token": 4.2e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -42527,13 +42563,13 @@ "max_output_tokens": 8000 }, "openrouter/minimax/minimax-m2": { - "input_cost_per_token": 2.55e-07, + "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 176947, + "max_tokens": 176947, "mode": "chat", - "output_cost_per_token": 1.02e-06, + "output_cost_per_token": 1.2e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -42739,14 +42775,14 @@ "supports_web_search": false }, "openrouter/nvidia/nemotron-3.5-lightning": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 8e-08, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 6e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2e-07, + "output_cost_per_token": 1.6e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -43199,14 +43235,14 @@ "supports_web_search": true }, "openrouter/openai/gpt-5.6-sol-pro": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 4e-07, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "input_cost_per_token_above_272k_tokens": 8e-06, + "output_cost_per_token_above_272k_tokens": 3e-05, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, "litellm_provider": "openrouter", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -43264,6 +43300,7 @@ "supports_web_search": false }, "openrouter/openai/gpt-oss-20b": { + "cache_read_input_token_cost": 9e-09, "input_cost_per_token": 1.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 131072, @@ -49891,7 +49928,8 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/claude-sonnet-5": { "deprecation_date": "2026-12-24", @@ -49999,7 +50037,8 @@ "supports_vision": true, "supports_native_streaming": true, "prompt_cache_min_tokens": 1024, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, @@ -60514,6 +60553,9 @@ "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1e-06, "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { @@ -60536,6 +60578,7 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, @@ -64006,7 +64049,7 @@ "groq/qwen/qwen3.8-27b": { "input_cost_per_token": 8e-07, "litellm_provider": "groq", - "max_input_tokens": 131042, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -67212,13 +67255,13 @@ "supports_web_search": false }, "openrouter/deepseek/deepseek-v4-flash-vision-exp": { - "input_cost_per_token": 4.4e-07, - "output_cost_per_token": 1.32e-06, - "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 2.156e-07, + "output_cost_per_token": 6.468e-07, + "cache_read_input_token_cost": 6.86e-09, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, @@ -67232,13 +67275,13 @@ "supports_web_search": false }, "openrouter/z-ai/glm-5.3": { - "input_cost_per_token": 3.556e-07, - "output_cost_per_token": 2.574e-06, - "cache_read_input_token_cost": 6.604e-08, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, "litellm_provider": "openrouter", "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, + "max_output_tokens": 943717, + "max_tokens": 943717, "mode": "chat", "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, @@ -67370,7 +67413,7 @@ }, "openrouter/deepseek/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 2.1e-08, + "input_cost_per_token": 1.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, @@ -67964,9 +68007,9 @@ "supports_web_search": false }, "openrouter/moonshotai/kimi-k2.6": { - "input_cost_per_token": 9.5e-07, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 3.41e-06, + "cache_read_input_token_cost": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 235929, @@ -69207,12 +69250,12 @@ }, "openrouter/qwen/qwen3-30b-a3b": { "deprecation_date": "2026-10-09", - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, @@ -69247,8 +69290,8 @@ }, "openrouter/qwen/qwen3-14b": { "deprecation_date": "2026-10-09", - "input_cost_per_token": 2.275e-07, - "output_cost_per_token": 9.1e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 2.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 16384, @@ -69878,7 +69921,9 @@ "vertex_ai/gemini-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 3e-06, "input_cost_per_token": 5e-07, + "input_cost_per_video_token": 3e-06, "litellm_provider": "vertex_ai", "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, @@ -70678,17 +70723,17 @@ }, "azure/eu/gpt-6-astra": { "deprecation_date": "2028-01-11", - "cache_creation_input_token_cost": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, - "cache_read_input_token_cost": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, - "input_cost_per_token": 1.1e-05, - "input_cost_per_token_above_272k_tokens": 2.2e-05, + "cache_creation_input_token_cost": 1.5e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3e-05, + "cache_read_input_token_cost": 1.2e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-06, + "input_cost_per_token": 1.2e-05, + "input_cost_per_token_above_272k_tokens": 2.4e-05, "litellm_provider": "azure", "mode": "chat", - "output_cost_per_token": 5.5e-05, - "output_cost_per_token_above_272k_tokens": 8.25e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "output_cost_per_token": 6e-05, + "output_cost_per_token_above_272k_tokens": 9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'swedencentral'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true }, "azure/eu/gpt-6-luna": { @@ -72821,17 +72866,17 @@ "supports_web_search": true }, "openrouter/~x-ai/grok-latest": { - "cache_read_input_token_cost": 4e-07, - "cache_read_input_token_cost_above_200k_tokens": 8e-07, - "input_cost_per_token": 1.6e-06, - "input_cost_per_token_above_200k_tokens": 3.2e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "openrouter", "max_input_tokens": 500000, "max_output_tokens": 450000, "max_tokens": 450000, "mode": "chat", - "output_cost_per_token": 4.8e-06, - "output_cost_per_token_above_200k_tokens": 9.6e-06, + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -74106,7 +74151,7 @@ "cache_read_input_token_cost": 4.2e-09, "input_cost_per_token": 2.1e-08, "litellm_provider": "openrouter", - "max_input_tokens": 131072, + "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", @@ -76134,7 +76179,7 @@ "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "max_input_tokens": 524288, "max_output_tokens": 471859, "max_tokens": 471859, "mode": "chat", @@ -76154,7 +76199,7 @@ "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 4.5e-07, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "max_input_tokens": 524288, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", @@ -76371,6 +76416,7 @@ "supports_web_search": false }, "openrouter/prism-ml/ternary-bonsai-2-27b": { + "cache_read_input_token_cost": 3.75e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, @@ -76431,17 +76477,17 @@ "supports_web_search": false }, "openrouter/x-ai/grok-4.7": { - "cache_read_input_token_cost": 4e-07, - "cache_read_input_token_cost_above_200k_tokens": 8e-07, - "input_cost_per_token": 1.6e-06, - "input_cost_per_token_above_200k_tokens": 3.2e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "openrouter", "max_input_tokens": 500000, "max_output_tokens": 450000, "max_tokens": 450000, "mode": "chat", - "output_cost_per_token": 4.8e-06, - "output_cost_per_token_above_200k_tokens": 9.6e-06, + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -76454,16 +76500,16 @@ "supports_web_search": true }, "moonshotai.kimi-k3": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, + "cache_creation_input_token_cost": 4.125e-06, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token": 1.65e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_prompt_caching": true, @@ -79026,6 +79072,28 @@ "supports_tool_choice": true, "supports_vision": true }, + "openrouter/anthropic/claude-sonnet-5.5:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "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, + "supports_web_search": true + }, "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 6e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index c147f4bf94b..81c0c045a30 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -12260,7 +12260,7 @@ "azure_ai/deepseek-v3.2": { "input_cost_per_token": 5.8e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 163840, + "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -12368,7 +12368,7 @@ "azure_ai/grok-4": { "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, + "max_input_tokens": 262000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -12490,7 +12490,7 @@ "azure_ai/grok-code-fast-1": { "input_cost_per_token": 2e-07, "litellm_provider": "azure_ai", - "max_input_tokens": 131072, + "max_input_tokens": 256000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", @@ -27518,7 +27518,8 @@ "search_context_size_high": 0.035 }, "gemini_native_audio": true, - "input_cost_per_image_token": 3e-06 + "input_cost_per_image_token": 3e-06, + "input_cost_per_video_token": 3e-06 }, "gemini-live-2.5-flash-preview-native-audio-09-2025": { "input_cost_per_audio_token": 3e-06, @@ -28418,7 +28419,7 @@ "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 1e-05, + "output_cost_per_reasoning_token": 5e-06, "output_cost_per_token": 5e-06, "output_cost_per_token_batches": 2.5e-06, "search_context_cost_per_query": { @@ -29015,7 +29016,7 @@ "image" ], "supports_function_calling": false, - "supports_prompt_caching": true, + "supports_prompt_caching": false, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, @@ -29026,7 +29027,7 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "supports_reasoning": false + "supports_reasoning": true }, "gemini/nano-banana-pro-preview": { "input_cost_per_image": 0.0011, @@ -29104,8 +29105,8 @@ "image" ], "supports_function_calling": false, - "supports_prompt_caching": true, - "supports_reasoning": false, + "supports_prompt_caching": false, + "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, @@ -29115,7 +29116,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "supports_pdf_input": true }, "gemini/gemini-3.1-flash-lite-image": { "input_cost_per_image": 0.00028, @@ -29146,8 +29148,9 @@ "image" ], "supports_function_calling": false, + "supports_pdf_input": true, "supports_prompt_caching": false, - "supports_reasoning": false, + "supports_reasoning": true, "supports_response_schema": false, "supports_system_messages": true, "supports_vision": true, @@ -29159,17 +29162,15 @@ "input_cost_per_token": 2e-06, "input_cost_per_token_batches": 1e-06, "litellm_provider": "gemini", - "max_input_tokens": 65536, - "max_output_tokens": 32768, - "max_tokens": 32768, - "mode": "image_generation", - "output_cost_per_image": 0.134, - "output_cost_per_image_token": 0.00012, + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", "output_cost_per_token": 1.2e-05, "rpm": 1000, "tpm": 4000000, "output_cost_per_token_batches": 6e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/models/deep-research-pro-preview-12-2025", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -29177,11 +29178,12 @@ ], "supported_modalities": [ "text", - "image" + "image", + "audio", + "video" ], "supported_output_modalities": [ - "text", - "image" + "text" ], "supports_function_calling": false, "supports_prompt_caching": true, @@ -29193,7 +29195,8 @@ "search_context_size_low": 0.035, "search_context_size_medium": 0.035, "search_context_size_high": 0.035 - } + }, + "supports_pdf_input": true }, "gemini/gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, @@ -30785,11 +30788,15 @@ ] }, "github_copilot/claude-haiku-4.5": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 5e-06, "supported_endpoints": [ "/v1/chat/completions" ], @@ -30838,11 +30845,15 @@ "supports_vision": true }, "github_copilot/claude-sonnet-4": { + "cache_creation_input_token_cost": 3.75e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 16000, "max_tokens": 16000, "mode": "chat", + "output_cost_per_token": 1.5e-05, "supported_endpoints": [ "/v1/chat/completions" ], @@ -31003,11 +31014,14 @@ "supports_vision": true }, "github_copilot/gpt-5-mini": { + "cache_read_input_token_cost": 2.5e-08, + "input_cost_per_token": 2.5e-07, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", + "output_cost_per_token": 2e-06, "supports_function_calling": true, "supports_parallel_function_calling": true, "supports_response_schema": true, @@ -31058,11 +31072,14 @@ "supports_vision": true }, "github_copilot/gpt-5.3-codex": { + "cache_read_input_token_cost": 1.75e-07, + "input_cost_per_token": 1.75e-06, "litellm_provider": "github_copilot", "max_input_tokens": 128000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", + "output_cost_per_token": 1.4e-05, "supported_endpoints": [ "/v1/responses" ], @@ -32745,6 +32762,25 @@ "audio" ] }, + "gpt-4o-mini-tts-2025-03-20": { + "input_cost_per_token": 6e-07, + "litellm_provider": "openai", + "mode": "audio_speech", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_second": 0.00025, + "output_cost_per_token": 1e-05, + "source": "https://developers.openai.com/api/docs/models/gpt-4o-mini-tts", + "supported_endpoints": [ + "/v1/audio/speech" + ], + "supported_modalities": [ + "text", + "audio" + ], + "supported_output_modalities": [ + "audio" + ] + }, "gpt-4o-search-preview": { "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, @@ -42065,8 +42101,8 @@ "input_cost_per_token_cache_hit": 2e-08, "litellm_provider": "openrouter", "max_input_tokens": 163840, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 147456, + "max_tokens": 147456, "mode": "chat", "output_cost_per_token": 4.1e-07, "source": "https://openrouter.ai/api/v1/models", @@ -42146,14 +42182,14 @@ "supports_web_search": false }, "openrouter/deepseek/deepseek-v4.1-flash": { - "cache_read_input_token_cost": 3.135e-08, - "input_cost_per_token": 3.483e-08, + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 1.2e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -42173,7 +42209,7 @@ "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 3.5e-06, + "output_cost_per_token": 4.2e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -42527,13 +42563,13 @@ "max_output_tokens": 8000 }, "openrouter/minimax/minimax-m2": { - "input_cost_per_token": 2.55e-07, + "input_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 204800, - "max_output_tokens": 131072, - "max_tokens": 131072, + "max_output_tokens": 176947, + "max_tokens": 176947, "mode": "chat", - "output_cost_per_token": 1.02e-06, + "output_cost_per_token": 1.2e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -42739,14 +42775,14 @@ "supports_web_search": false }, "openrouter/nvidia/nemotron-3.5-lightning": { - "cache_read_input_token_cost": 4e-08, - "input_cost_per_token": 8e-08, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 6e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 235929, - "max_tokens": 235929, + "max_output_tokens": 32768, + "max_tokens": 32768, "mode": "chat", - "output_cost_per_token": 2e-07, + "output_cost_per_token": 1.6e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -43199,14 +43235,14 @@ "supports_web_search": true }, "openrouter/openai/gpt-5.6-sol-pro": { - "input_cost_per_token": 2e-06, - "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 2e-07, - "cache_creation_input_token_cost": 2.5e-06, - "cache_creation_input_token_cost_above_272k_tokens": 5e-06, - "input_cost_per_token_above_272k_tokens": 4e-06, - "output_cost_per_token_above_272k_tokens": 1.5e-05, - "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 4e-06, + "output_cost_per_token": 2e-05, + "cache_read_input_token_cost": 4e-07, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "input_cost_per_token_above_272k_tokens": 8e-06, + "output_cost_per_token_above_272k_tokens": 3e-05, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, "litellm_provider": "openrouter", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -43264,6 +43300,7 @@ "supports_web_search": false }, "openrouter/openai/gpt-oss-20b": { + "cache_read_input_token_cost": 9e-09, "input_cost_per_token": 1.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 131072, @@ -49891,7 +49928,8 @@ "supports_tool_choice": true, "supports_vision": true, "prompt_cache_min_tokens": 1024, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/claude-sonnet-5": { "deprecation_date": "2026-12-24", @@ -49999,7 +50037,8 @@ "supports_vision": true, "supports_native_streaming": true, "prompt_cache_min_tokens": 1024, - "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" + "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", + "cache_creation_input_token_cost_batches": 1.88e-06 }, "vertex_ai/mistralai/codestral-2@001": { "input_cost_per_token": 3e-07, @@ -60514,6 +60553,9 @@ "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 1e-06, "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_token": 5e-06, "search_context_cost_per_query": { @@ -60536,6 +60578,7 @@ ], "supports_audio_input": true, "supports_function_calling": true, + "supports_reasoning": true, "supports_video_input": true, "supports_vision": true, "supports_web_search": true, @@ -64006,7 +64049,7 @@ "groq/qwen/qwen3.8-27b": { "input_cost_per_token": 8e-07, "litellm_provider": "groq", - "max_input_tokens": 131042, + "max_input_tokens": 131072, "max_output_tokens": 16384, "max_tokens": 16384, "mode": "chat", @@ -67212,13 +67255,13 @@ "supports_web_search": false }, "openrouter/deepseek/deepseek-v4-flash-vision-exp": { - "input_cost_per_token": 4.4e-07, - "output_cost_per_token": 1.32e-06, - "cache_read_input_token_cost": 1.4e-08, + "input_cost_per_token": 2.156e-07, + "output_cost_per_token": 6.468e-07, + "cache_read_input_token_cost": 6.86e-09, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 943718, - "max_tokens": 943718, + "max_output_tokens": 262144, + "max_tokens": 262144, "mode": "chat", "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, @@ -67232,13 +67275,13 @@ "supports_web_search": false }, "openrouter/z-ai/glm-5.3": { - "input_cost_per_token": 3.556e-07, - "output_cost_per_token": 2.574e-06, - "cache_read_input_token_cost": 6.604e-08, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 2.6e-07, "litellm_provider": "openrouter", "max_input_tokens": 1310720, - "max_output_tokens": 943718, - "max_tokens": 943718, + "max_output_tokens": 943717, + "max_tokens": 943717, "mode": "chat", "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, @@ -67370,7 +67413,7 @@ }, "openrouter/deepseek/deepseek-v4-flash-0731": { "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 2.1e-08, + "input_cost_per_token": 1.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, @@ -67964,9 +68007,9 @@ "supports_web_search": false }, "openrouter/moonshotai/kimi-k2.6": { - "input_cost_per_token": 9.5e-07, - "output_cost_per_token": 4e-06, - "cache_read_input_token_cost": 1.6e-07, + "input_cost_per_token": 6.5e-07, + "output_cost_per_token": 3.41e-06, + "cache_read_input_token_cost": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 235929, @@ -69207,12 +69250,12 @@ }, "openrouter/qwen/qwen3-30b-a3b": { "deprecation_date": "2026-10-09", - "input_cost_per_token": 1.3e-07, - "output_cost_per_token": 5.2e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 5e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, - "max_output_tokens": 8192, - "max_tokens": 8192, + "max_output_tokens": 16384, + "max_tokens": 16384, "mode": "chat", "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, @@ -69247,8 +69290,8 @@ }, "openrouter/qwen/qwen3-14b": { "deprecation_date": "2026-10-09", - "input_cost_per_token": 2.275e-07, - "output_cost_per_token": 9.1e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 2.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 16384, @@ -69878,7 +69921,9 @@ "vertex_ai/gemini-2.5-flash-native-audio": { "deprecation_date": "2026-12-13", "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 3e-06, "input_cost_per_token": 5e-07, + "input_cost_per_video_token": 3e-06, "litellm_provider": "vertex_ai", "mode": "realtime", "output_cost_per_audio_token": 1.2e-05, @@ -70678,17 +70723,17 @@ }, "azure/eu/gpt-6-astra": { "deprecation_date": "2028-01-11", - "cache_creation_input_token_cost": 1.375e-05, - "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05, - "cache_read_input_token_cost": 1.1e-06, - "cache_read_input_token_cost_above_272k_tokens": 2.2e-06, - "input_cost_per_token": 1.1e-05, - "input_cost_per_token_above_272k_tokens": 2.2e-05, + "cache_creation_input_token_cost": 1.5e-05, + "cache_creation_input_token_cost_above_272k_tokens": 3e-05, + "cache_read_input_token_cost": 1.2e-06, + "cache_read_input_token_cost_above_272k_tokens": 2.4e-06, + "input_cost_per_token": 1.2e-05, + "input_cost_per_token_above_272k_tokens": 2.4e-05, "litellm_provider": "azure", "mode": "chat", - "output_cost_per_token": 5.5e-05, - "output_cost_per_token_above_272k_tokens": 8.25e-05, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "output_cost_per_token": 6e-05, + "output_cost_per_token_above_272k_tokens": 9e-05, + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'swedencentral'%20and%20priceType%20eq%20'Consumption'", "supports_reasoning": true }, "azure/eu/gpt-6-luna": { @@ -72821,17 +72866,17 @@ "supports_web_search": true }, "openrouter/~x-ai/grok-latest": { - "cache_read_input_token_cost": 4e-07, - "cache_read_input_token_cost_above_200k_tokens": 8e-07, - "input_cost_per_token": 1.6e-06, - "input_cost_per_token_above_200k_tokens": 3.2e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "openrouter", "max_input_tokens": 500000, "max_output_tokens": 450000, "max_tokens": 450000, "mode": "chat", - "output_cost_per_token": 4.8e-06, - "output_cost_per_token_above_200k_tokens": 9.6e-06, + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -74106,7 +74151,7 @@ "cache_read_input_token_cost": 4.2e-09, "input_cost_per_token": 2.1e-08, "litellm_provider": "openrouter", - "max_input_tokens": 131072, + "max_input_tokens": 262144, "max_output_tokens": 32768, "max_tokens": 32768, "mode": "chat", @@ -76134,7 +76179,7 @@ "cache_read_input_token_cost": 1.7e-07, "input_cost_per_token": 1e-06, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "max_input_tokens": 524288, "max_output_tokens": 471859, "max_tokens": 471859, "mode": "chat", @@ -76154,7 +76199,7 @@ "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 4.5e-07, "litellm_provider": "openrouter", - "max_input_tokens": 1048576, + "max_input_tokens": 524288, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", @@ -76371,6 +76416,7 @@ "supports_web_search": false }, "openrouter/prism-ml/ternary-bonsai-2-27b": { + "cache_read_input_token_cost": 3.75e-08, "input_cost_per_token": 7.5e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, @@ -76431,17 +76477,17 @@ "supports_web_search": false }, "openrouter/x-ai/grok-4.7": { - "cache_read_input_token_cost": 4e-07, - "cache_read_input_token_cost_above_200k_tokens": 8e-07, - "input_cost_per_token": 1.6e-06, - "input_cost_per_token_above_200k_tokens": 3.2e-06, + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_200k_tokens": 1e-06, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "openrouter", "max_input_tokens": 500000, "max_output_tokens": 450000, "max_tokens": 450000, "mode": "chat", - "output_cost_per_token": 4.8e-06, - "output_cost_per_token_above_200k_tokens": 9.6e-06, + "output_cost_per_token": 6e-06, + "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -76454,16 +76500,16 @@ "supports_web_search": true }, "moonshotai.kimi-k3": { - "cache_creation_input_token_cost": 3.75e-06, - "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, + "cache_creation_input_token_cost": 4.125e-06, + "cache_read_input_token_cost": 3.3e-07, + "input_cost_per_token": 3.3e-06, "litellm_provider": "bedrock_converse", "max_input_tokens": 1000000, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.5e-05, - "source": "https://aws.amazon.com/bedrock/pricing/", + "output_cost_per_token": 1.65e-05, + "source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json", "supports_audio_input": false, "supports_function_calling": true, "supports_prompt_caching": true, @@ -79026,6 +79072,28 @@ "supports_tool_choice": true, "supports_vision": true }, + "openrouter/anthropic/claude-sonnet-5.5:batch": { + "cache_creation_input_token_cost": 1.25e-06, + "cache_creation_input_token_cost_above_1hr": 2e-06, + "cache_read_input_token_cost": 1e-07, + "input_cost_per_token": 1e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-06, + "source": "https://openrouter.ai/api/v1/models", + "supports_audio_input": false, + "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, + "supports_web_search": true + }, "baseten/deepseek-ai/DeepSeek-V4.1-Flash-Fast": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 6e-07, diff --git a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py index 0afd989272e..088247c2ea4 100644 --- a/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py +++ b/tests/unit/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py @@ -1145,6 +1145,35 @@ def test_generic_cost_per_token_gpt54_above_272k_tokens(_local_model_cost_map): assert round(completion_cost, 10) == round(expected_completion, 10) +@pytest.mark.parametrize( + ("prompt_tokens", "input_rate", "cache_read_rate", "output_rate"), + [ + (100_000, 1.2e-05, 1.2e-06, 6e-05), + (300_000, 2.4e-05, 2.4e-06, 9e-05), + ], +) +def test_generic_cost_per_token_azure_eu_gpt_6_astra_tiers( + _local_model_cost_map, prompt_tokens, input_rate, cache_read_rate, output_rate +): + """azure/eu/gpt-6-astra bills Azure's Data Zone rates, doubling input and cache read past 272K.""" + cached_tokens = 20_000 + completion_tokens = 1_000 + usage = Usage( + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + total_tokens=prompt_tokens + completion_tokens, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=cached_tokens), + ) + prompt_cost, completion_cost = generic_cost_per_token( + model="azure/eu/gpt-6-astra", + usage=usage, + custom_llm_provider="azure", + ) + expected_prompt = (prompt_tokens - cached_tokens) * input_rate + cached_tokens * cache_read_rate + assert prompt_cost == pytest.approx(expected_prompt) + assert completion_cost == pytest.approx(completion_tokens * output_rate) + + def test_generic_cost_per_token_minimax_m3_above_512k_tokens(_local_model_cost_map): """MiniMax-M3: prompts >512K input tokens priced at 2x input, output, and cache read.""" model = "minimax/MiniMax-M3"