From e30f9f578c9af0dd48b837a318a6246ad6e2f23e Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 22 Sep 2026 14:05:33 -0700 Subject: [PATCH] fix(model_prices): registry audit 2026-09-22, absorb open pricing PRs (#42543) * fix(model_prices): registry audit 2026-09-22, absorb open pricing PRs Rolls the open registry-only PRs into one PR after re-verifying every value against the official provider source: OpenAI, Azure, Vertex AI and Gemini batch cache-read prices, Baseten model metadata from the authenticated inference API, Bedrock eu-west-2 Nemotron Super 3 pricing from the AWS offer file, and OpenRouter prices refreshed from the live OpenRouter models API Co-authored-by: sinksilk <785976238@qq.com> Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): add groq/llama-guard-3-8b from the Groq model page Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): refresh openrouter deepseek aliases from live api and drop stale off-peak windows Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(model_prices): resolve baseten merge conflicts against main Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Co-authored-by: sinksilk <785976238@qq.com> --- ...odel_prices_and_context_window_backup.json | 376 ++++++++++++++---- model_prices_and_context_window.json | 376 ++++++++++++++---- tests/test_litellm/test_cost_calculator.py | 24 ++ 3 files changed, 608 insertions(+), 168 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index b725094ae91..94786f250b0 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -4417,7 +4417,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-08 }, "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, @@ -4456,7 +4457,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/eu/gpt-5.1": { "deprecation_date": "2027-05-15", @@ -4636,7 +4638,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, @@ -6094,7 +6097,8 @@ "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5.1-chat-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -6282,7 +6286,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -6460,7 +6465,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "azure/gpt-5-nano": { "deprecation_date": "2027-02-09", @@ -6533,7 +6539,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.5e-09 }, "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", @@ -6822,7 +6829,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 8.75e-08 }, "azure/gpt-5.2-chat": { "cache_read_input_token_cost": 1.75e-07, @@ -7287,7 +7295,11 @@ "output_cost_per_token_flex": 7.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.3e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.125e-05 }, "azure/us/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.75e-07, @@ -7333,7 +7345,11 @@ "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/eu/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.75e-07, @@ -7379,7 +7395,11 @@ "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/gpt-5.4-pro": { "deprecation_date": "2027-09-07", @@ -7477,7 +7497,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "input_cost_per_token_above_272k_tokens_batches": 3e-05, + "output_cost_per_token_above_272k_tokens_batches": 0.000135 }, "azure/gpt-5.6": { "cache_creation_input_token_cost": 6.25e-06, @@ -8900,7 +8922,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token_above_272k_tokens_batches": 5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.25e-05 }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -9003,7 +9029,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -9106,7 +9136,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -9293,7 +9327,8 @@ "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_priority": 9e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 3.75e-08 }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", @@ -9390,7 +9425,8 @@ "output_cost_per_token_batches": 6.25e-07, "output_cost_per_token_flex": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { "cache_read_input_token_cost": 1.25e-06, @@ -10404,7 +10440,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-08 }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, @@ -10443,7 +10480,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/us/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, @@ -10479,7 +10517,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/us/gpt-5.1": { "deprecation_date": "2027-05-15", @@ -12908,6 +12947,23 @@ "supports_tool_choice": true, "output_cost_per_token": 1.86e-06 }, + "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.01e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-07, "litellm_provider": "bedrock", @@ -26782,7 +26838,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_batches": 1e-07 }, "gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -26867,7 +26924,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_batches": 2.5e-08 }, "gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -26946,7 +27004,8 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, @@ -27055,7 +27114,8 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -27112,7 +27172,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 1.5e-08 }, "deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -27147,7 +27208,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "cache_read_input_token_cost_batches": 1e-07 }, "gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, @@ -27880,7 +27942,8 @@ "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_batches": 7.5e-08 }, "vertex_ai/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -27937,7 +28000,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, @@ -27995,7 +28059,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, @@ -28053,7 +28118,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, @@ -30385,7 +30451,8 @@ "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_batches": 7.5e-08 }, "gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -30442,7 +30509,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, @@ -30500,7 +30568,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, @@ -30558,7 +30627,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, @@ -35661,7 +35731,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -36087,7 +36158,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gpt-5-nano": { "cache_read_input_token_cost": 5e-09, @@ -36186,7 +36258,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 2.5e-09 }, "gpt-image-1": { "cache_read_input_token_cost": 1.25e-06, @@ -36809,6 +36882,15 @@ "supports_response_schema": false, "supports_tool_choice": true }, + "groq/llama-guard-3-8b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://console.groq.com/docs/model/llama-guard-3-8b" + }, "groq/gemma-7b-it": { "deprecation_date": "2024-12-18", "input_cost_per_token": 5e-08, @@ -43157,6 +43239,28 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "openrouter/anthropic/claude-opus-5.5": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "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 + }, "openrouter/bytedance/ui-tars-1.5-7b": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-07, @@ -43328,21 +43432,21 @@ "supports_web_search": false }, "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 9.31074e-07, + "input_cost_per_token": 8.92272e-07, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.862148e-06, + "output_cost_per_token": 1.784544e-06, "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "cache_read_input_token_cost": 7.75895e-08, + "cache_read_input_token_cost": 7.4356e-08, "supports_audio_input": false, "supports_pdf_input": false, "supports_vision": false, @@ -52043,7 +52147,8 @@ "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "supports_reasoning": false, - "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_read_input_token_cost_batches": 1e-07 }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -52080,7 +52185,8 @@ "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "supports_reasoning": false, - "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_read_input_token_cost_batches": 2.5e-08 }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -52135,7 +52241,8 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "vertex_ai/gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, @@ -52245,7 +52352,8 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-08 }, "vertex_ai/gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -52303,7 +52411,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 1.5e-08 }, "vertex_ai/deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -52319,7 +52428,8 @@ "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, - "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_read_input_token_cost_batches": 1e-07 }, "vertex_ai/imagegeneration@006": { "deprecation_date": "2025-09-24", @@ -69143,13 +69253,13 @@ "supports_web_search": false }, "openrouter/qwen/qwen3.6-27b": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 262140, + "max_tokens": 262140, "mode": "chat", "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, @@ -73178,16 +73288,16 @@ "supports_web_search": true }, "openrouter/~anthropic/claude-opus-latest": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.5e-05, + "output_cost_per_token": 2e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73222,15 +73332,14 @@ "supports_web_search": true }, "openrouter/~deepseek/deepseek-flash-latest": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 1.2e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9}, - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 4.8e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73243,15 +73352,14 @@ "supports_web_search": false }, "openrouter/~deepseek/deepseek-pro-latest": { - "cache_read_input_token_cost": 4.4e-08, - "input_cost_per_token": 1.32e-06, + "cache_read_input_token_cost": 1.2726e-08, + "input_cost_per_token": 3.9996e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":6.6e-7,"output_cost_per_token":0.00000198,"cache_read_input_token_cost":2.2e-8}, - "output_cost_per_token": 3.96e-06, + "output_cost_per_token": 1.19988e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73264,14 +73372,14 @@ "supports_web_search": false }, "openrouter/~deepseek/deepseek-v4-flash-latest": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 4e-08, + "cache_read_input_token_cost": 8e-09, + "input_cost_per_token": 3e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 6.4e-07, + "output_cost_per_token": 8e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73334,13 +73442,13 @@ }, "openrouter/~moonshotai/kimi-latest": { "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, + "input_cost_per_token": 1.4989e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.0758e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73378,19 +73486,19 @@ "supports_web_search": true }, "openrouter/~openai/gpt-luna-latest": { - "cache_creation_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5e-07, - "cache_read_input_token_cost": 2e-08, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_272k_tokens": 4e-07, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, "litellm_provider": "openrouter", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73496,14 +73604,14 @@ "supports_web_search": true }, "openrouter/~z-ai/glm-flash-latest": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -75959,6 +76067,106 @@ "supports_vision": true, "supports_web_search": true }, + "openrouter/openai/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "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 + }, + "openrouter/openai/gpt-6-luna-pro": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "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 + }, + "openrouter/openai/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "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 + }, + "openrouter/openai/gpt-6-sol-pro": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "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 + }, "openrouter/openai/o3-mini:batch": { "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 5.5e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index b725094ae91..94786f250b0 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -4417,7 +4417,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-08 }, "azure/eu/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, @@ -4456,7 +4457,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/eu/gpt-5.1": { "deprecation_date": "2027-05-15", @@ -4636,7 +4638,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/eu/o1-2024-12-17": { "cache_read_input_token_cost": 8.25e-06, @@ -6094,7 +6097,8 @@ "input_cost_per_token_batches": 6.25e-07, "output_cost_per_token_batches": 5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5.1-chat-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -6282,7 +6286,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "azure/gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -6460,7 +6465,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "azure/gpt-5-nano": { "deprecation_date": "2027-02-09", @@ -6533,7 +6539,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.5e-09 }, "azure/gpt-5-pro": { "deprecation_date": "2027-04-07", @@ -6822,7 +6829,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 8.75e-08 }, "azure/gpt-5.2-chat": { "cache_read_input_token_cost": 1.75e-07, @@ -7287,7 +7295,11 @@ "output_cost_per_token_flex": 7.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.3e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.125e-05 }, "azure/us/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.75e-07, @@ -7333,7 +7345,11 @@ "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/eu/gpt-5.4-2026-03-05": { "cache_read_input_token_cost": 2.75e-07, @@ -7379,7 +7395,11 @@ "output_cost_per_token_batches": 8.25e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_xhigh_reasoning_effort": true, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_above_272k_tokens_batches": 2.75e-07, + "cache_read_input_token_cost_batches": 1.43e-07, + "input_cost_per_token_above_272k_tokens_batches": 2.75e-06, + "output_cost_per_token_above_272k_tokens_batches": 1.2375e-05 }, "azure/gpt-5.4-pro": { "deprecation_date": "2027-09-07", @@ -7477,7 +7497,9 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "input_cost_per_token_above_272k_tokens_batches": 3e-05, + "output_cost_per_token_above_272k_tokens_batches": 0.000135 }, "azure/gpt-5.6": { "cache_creation_input_token_cost": 6.25e-06, @@ -8900,7 +8922,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07, + "cache_read_input_token_cost_batches": 2.5e-07, + "input_cost_per_token_above_272k_tokens_batches": 5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.25e-05 }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -9003,7 +9029,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -9106,7 +9136,11 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", + "cache_read_input_token_cost_above_272k_tokens_batches": 5.5e-07, + "cache_read_input_token_cost_batches": 2.75e-07, + "input_cost_per_token_above_272k_tokens_batches": 5.5e-06, + "output_cost_per_token_above_272k_tokens_batches": 2.475e-05 }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -9293,7 +9327,8 @@ "output_cost_per_token_flex": 2.25e-06, "output_cost_per_token_priority": 9e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 3.75e-08 }, "azure/gpt-5.4-nano": { "deprecation_date": "2027-09-21", @@ -9390,7 +9425,8 @@ "output_cost_per_token_batches": 6.25e-07, "output_cost_per_token_flex": 6.25e-07, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", - "supports_xhigh_reasoning_effort": true + "supports_xhigh_reasoning_effort": true, + "cache_read_input_token_cost_batches": 1e-08 }, "azure/gpt-image-1": { "cache_read_input_token_cost": 1.25e-06, @@ -10404,7 +10440,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 6.875e-08 }, "azure/us/gpt-5-mini-2025-08-07": { "cache_read_input_token_cost": 2.75e-08, @@ -10443,7 +10480,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.375e-08 }, "azure/us/gpt-5-nano-2025-08-07": { "cache_read_input_token_cost": 5.5e-09, @@ -10479,7 +10517,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 2.75e-09 }, "azure/us/gpt-5.1": { "deprecation_date": "2027-05-15", @@ -12908,6 +12947,23 @@ "supports_tool_choice": true, "output_cost_per_token": 1.86e-06 }, + "bedrock/eu-west-2/nvidia.nemotron-super-3-120b": { + "input_cost_per_token": 2.3e-07, + "litellm_provider": "bedrock", + "max_input_tokens": 256000, + "max_output_tokens": 32000, + "max_tokens": 32000, + "mode": "chat", + "output_cost_per_token": 1.01e-06, + "source": "https://aws.amazon.com/bedrock/pricing/", + "supports_audio_input": false, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": false + }, "bedrock/eu-west-2/qwen.qwen3-coder-next": { "input_cost_per_token": 7.8e-07, "litellm_provider": "bedrock", @@ -26782,7 +26838,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_batches": 1e-07 }, "gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -26867,7 +26924,8 @@ "search_context_size_medium": 0.014, "search_context_size_high": 0.014 }, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_batches": 2.5e-08 }, "gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -26946,7 +27004,8 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, @@ -27055,7 +27114,8 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -27112,7 +27172,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 1.5e-08 }, "deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -27147,7 +27208,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_vision": true, - "supports_web_search": true + "supports_web_search": true, + "cache_read_input_token_cost_batches": 1e-07 }, "gemini-2.5-flash-lite": { "cache_read_input_audio_token_cost": 3e-08, @@ -27880,7 +27942,8 @@ "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_batches": 7.5e-08 }, "vertex_ai/gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -27937,7 +28000,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, @@ -27995,7 +28059,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, @@ -28053,7 +28118,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "vertex_ai/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, @@ -30385,7 +30451,8 @@ "output_cost_per_token_batches": 4.5e-06, "input_cost_per_token_flex": 7.5e-07, "output_cost_per_token_flex": 4.5e-06, - "cache_read_input_token_cost_flex": 7.5e-08 + "cache_read_input_token_cost_flex": 7.5e-08, + "cache_read_input_token_cost_batches": 7.5e-08 }, "gemini-3.6-flash": { "prompt_cache_min_tokens": 4096, @@ -30442,7 +30509,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini-3.7-flash": { "prompt_cache_min_tokens": 4096, @@ -30500,7 +30568,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini-3.8-flash": { "prompt_cache_min_tokens": 4096, @@ -30558,7 +30627,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 3.75e-08 }, "gemini/gemini-2.5-pro-preview-tts": { "cache_read_input_token_cost": 1.25e-07, @@ -35661,7 +35731,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 6.25e-08 }, "gpt-5-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -36087,7 +36158,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "gpt-5-nano": { "cache_read_input_token_cost": 5e-09, @@ -36186,7 +36258,8 @@ "supports_web_search": true, "supports_none_reasoning_effort": false, "supports_xhigh_reasoning_effort": false, - "supports_minimal_reasoning_effort": true + "supports_minimal_reasoning_effort": true, + "cache_read_input_token_cost_batches": 2.5e-09 }, "gpt-image-1": { "cache_read_input_token_cost": 1.25e-06, @@ -36809,6 +36882,15 @@ "supports_response_schema": false, "supports_tool_choice": true }, + "groq/llama-guard-3-8b": { + "input_cost_per_token": 2e-07, + "litellm_provider": "groq", + "max_input_tokens": 8192, + "max_tokens": 8192, + "mode": "chat", + "output_cost_per_token": 2e-07, + "source": "https://console.groq.com/docs/model/llama-guard-3-8b" + }, "groq/gemma-7b-it": { "deprecation_date": "2024-12-18", "input_cost_per_token": 5e-08, @@ -43157,6 +43239,28 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "openrouter/anthropic/claude-opus-5.5": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1000000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "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 + }, "openrouter/bytedance/ui-tars-1.5-7b": { "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 1e-07, @@ -43328,21 +43432,21 @@ "supports_web_search": false }, "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 9.31074e-07, + "input_cost_per_token": 8.92272e-07, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.862148e-06, + "output_cost_per_token": 1.784544e-06, "source": "https://openrouter.ai/api/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "cache_read_input_token_cost": 7.75895e-08, + "cache_read_input_token_cost": 7.4356e-08, "supports_audio_input": false, "supports_pdf_input": false, "supports_vision": false, @@ -52043,7 +52147,8 @@ "output_cost_per_token_flex": 6e-06, "output_cost_per_token_priority": 2.16e-05, "supports_reasoning": false, - "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_read_input_token_cost_batches": 1e-07 }, "vertex_ai/gemini-3-pro-image-preview": { "input_cost_per_image": 0.0011, @@ -52080,7 +52185,8 @@ "output_cost_per_token_batches": 1.5e-06, "output_cost_per_token_flex": 1.5e-06, "supports_reasoning": false, - "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_read_input_token_cost_batches": 2.5e-08 }, "vertex_ai/gemini-3.1-flash-image-preview": { "input_cost_per_image": 0.00056, @@ -52135,7 +52241,8 @@ "supports_response_schema": false, "supports_system_messages": true, "supports_video_input": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost_batches": 1.25e-08 }, "vertex_ai/gemini-3.1-flash-lite-preview": { "cache_read_input_token_cost": 2.5e-08, @@ -52245,7 +52352,8 @@ }, "web_search_billing_unit": "per_query", "google_maps_grounding_cost_per_query": 0.014, - "input_cost_per_audio_token_batches": 2.5e-07 + "input_cost_per_audio_token_batches": 2.5e-07, + "cache_read_input_token_cost_batches": 1.25e-08 }, "vertex_ai/gemini-3.5-flash-lite": { "deprecation_date": "2027-07-21", @@ -52303,7 +52411,8 @@ "search_context_size_high": 0.014 }, "web_search_billing_unit": "per_query", - "google_maps_grounding_cost_per_query": 0.014 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_batches": 1.5e-08 }, "vertex_ai/deep-research-pro-preview-12-2025": { "cache_read_input_token_cost": 2e-07, @@ -52319,7 +52428,8 @@ "output_cost_per_image_token": 0.00012, "output_cost_per_token": 1.2e-05, "output_cost_per_token_batches": 6e-06, - "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_read_input_token_cost_batches": 1e-07 }, "vertex_ai/imagegeneration@006": { "deprecation_date": "2025-09-24", @@ -69143,13 +69253,13 @@ "supports_web_search": false }, "openrouter/qwen/qwen3.6-27b": { - "input_cost_per_token": 3e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3.2e-07, + "output_cost_per_token": 2.7e-06, + "cache_read_input_token_cost": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, - "max_output_tokens": 65536, - "max_tokens": 65536, + "max_output_tokens": 262140, + "max_tokens": 262140, "mode": "chat", "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, @@ -73178,16 +73288,16 @@ "supports_web_search": true }, "openrouter/~anthropic/claude-opus-latest": { - "cache_creation_input_token_cost": 6.25e-06, - "cache_creation_input_token_cost_above_1hr": 1e-05, - "cache_read_input_token_cost": 5e-07, - "input_cost_per_token": 5e-06, + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_1hr": 8e-06, + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2.5e-05, + "output_cost_per_token": 2e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73222,15 +73332,14 @@ "supports_web_search": true }, "openrouter/~deepseek/deepseek-flash-latest": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 3.6e-09, + "input_cost_per_token": 1.2e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 943718, + "max_tokens": 943718, "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":1.5e-7,"output_cost_per_token":6e-7,"cache_read_input_token_cost":3e-9}, - "output_cost_per_token": 1.2e-06, + "output_cost_per_token": 4.8e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73243,15 +73352,14 @@ "supports_web_search": false }, "openrouter/~deepseek/deepseek-pro-latest": { - "cache_read_input_token_cost": 4.4e-08, - "input_cost_per_token": 1.32e-06, + "cache_read_input_token_cost": 1.2726e-08, + "input_cost_per_token": 3.9996e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, - "max_output_tokens": 384000, - "max_tokens": 384000, + "max_output_tokens": 393216, + "max_tokens": 393216, "mode": "chat", - "off_peak_pricing": {"windows":[{"weekdays":["saturday","sunday"],"hours_utc":"00:00-00:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"00:00-01:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"04:00-06:00"},{"weekdays":["monday","tuesday","wednesday","thursday","friday"],"hours_utc":"10:00-00:00"}],"input_cost_per_token":6.6e-7,"output_cost_per_token":0.00000198,"cache_read_input_token_cost":2.2e-8}, - "output_cost_per_token": 3.96e-06, + "output_cost_per_token": 1.19988e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73264,14 +73372,14 @@ "supports_web_search": false }, "openrouter/~deepseek/deepseek-v4-flash-latest": { - "cache_read_input_token_cost": 1.6e-08, - "input_cost_per_token": 4e-08, + "cache_read_input_token_cost": 8e-09, + "input_cost_per_token": 3e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 6.4e-07, + "output_cost_per_token": 8e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73334,13 +73442,13 @@ }, "openrouter/~moonshotai/kimi-latest": { "cache_read_input_token_cost": 3e-07, - "input_cost_per_token": 3e-06, + "input_cost_per_token": 1.4989e-06, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 1.5e-05, + "output_cost_per_token": 1.0758e-05, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73378,19 +73486,19 @@ "supports_web_search": true }, "openrouter/~openai/gpt-luna-latest": { - "cache_creation_input_token_cost": 2.5e-07, - "cache_creation_input_token_cost_above_272k_tokens": 5e-07, - "cache_read_input_token_cost": 2e-08, - "cache_read_input_token_cost_above_272k_tokens": 4e-08, - "input_cost_per_token": 2e-07, - "input_cost_per_token_above_272k_tokens": 4e-07, + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, "litellm_provider": "openrouter", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.2e-06, - "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73496,14 +73604,14 @@ "supports_web_search": true }, "openrouter/~z-ai/glm-flash-latest": { - "cache_read_input_token_cost": 5e-08, - "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 1.5e-08, + "input_cost_per_token": 7.5e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, "max_tokens": 943718, "mode": "chat", - "output_cost_per_token": 5e-07, + "output_cost_per_token": 2.5e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -75959,6 +76067,106 @@ "supports_vision": true, "supports_web_search": true }, + "openrouter/openai/gpt-6-luna": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "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 + }, + "openrouter/openai/gpt-6-luna-pro": { + "cache_creation_input_token_cost": 1.25e-07, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-07, + "cache_read_input_token_cost": 1e-08, + "cache_read_input_token_cost_above_272k_tokens": 2e-08, + "input_cost_per_token": 1e-07, + "input_cost_per_token_above_272k_tokens": 2e-07, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "output_cost_per_token_above_272k_tokens": 7.5e-07, + "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 + }, + "openrouter/openai/gpt-6-sol": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "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 + }, + "openrouter/openai/gpt-6-sol-pro": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "litellm_provider": "openrouter", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1e-05, + "output_cost_per_token_above_272k_tokens": 1.5e-05, + "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 + }, "openrouter/openai/o3-mini:batch": { "cache_read_input_token_cost": 2.75e-07, "input_cost_per_token": 5.5e-07, diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py index 7d2a04c500f..ecc01857f8c 100644 --- a/tests/test_litellm/test_cost_calculator.py +++ b/tests/test_litellm/test_cost_calculator.py @@ -4847,3 +4847,27 @@ def test_cost_per_token_bedrock_qwen3_next_uses_regional_entry_not_us_rate( assert prompt_usd == pytest.approx(prompt_tokens * regional["input_cost_per_token"]) assert completion_usd == pytest.approx(completion_tokens * regional["output_cost_per_token"]) + + +def test_cost_per_token_bedrock_nemotron_super_3_uses_eu_west_2_entry_not_us_rate( + monkeypatch: pytest.MonkeyPatch, +) -> None: + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url="")) + + regional_key: Final = "bedrock/eu-west-2/nvidia.nemotron-super-3-120b" + regional: Final = litellm.model_cost[regional_key] + us: Final = litellm.model_cost["nvidia.nemotron-super-3-120b"] + assert regional["input_cost_per_token"] != us["input_cost_per_token"] + assert regional["output_cost_per_token"] != us["output_cost_per_token"] + + prompt_tokens, completion_tokens = 1000, 500 + prompt_usd, completion_usd = cost_per_token( + model=regional_key, + prompt_tokens=prompt_tokens, + completion_tokens=completion_tokens, + custom_llm_provider="bedrock", + ) + + assert prompt_usd == pytest.approx(prompt_tokens * regional["input_cost_per_token"]) + assert completion_usd == pytest.approx(completion_tokens * regional["output_cost_per_token"])