From 834f187f4c9ea34be582b2e7315b93665124d9c0 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 14 Sep 2026 19:20:36 +0000 Subject: [PATCH 01/16] feat(models): add Together, Fireworks, Nebius, Cohere, Bedrock models and Inception cache pricing Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 88 +++++++++++++++++++ model_prices_and_context_window.json | 88 +++++++++++++++++++ 2 files changed, 176 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 89d582db151..0954f9360fa 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -352,6 +352,17 @@ "supports_function_calling": true, "supports_pdf_input": true }, + "writer.palmyra-vision-7b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-vision-7b.html", + "supports_vision": true + }, "amazon.nova-lite-v1:0": { "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", @@ -14650,6 +14661,21 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "command-a-plus-05-2026": { + "input_cost_per_token": 0.0, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.cohere.com/docs/command-a-plus", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "command-light": { "input_cost_per_token": 3e-07, "litellm_provider": "cohere_chat", @@ -34159,6 +34185,7 @@ "supports_tool_choice": true }, "inception/mercury-2.5": { + "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "inception", "max_input_tokens": 260000, @@ -34168,6 +34195,7 @@ "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true @@ -37333,6 +37361,15 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" }, + "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { + "input_cost_per_token": 1.32e-06, + "litellm_provider": "nebius", + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/MiniMaxAI/MiniMax-M2.5": { "max_tokens": 196608, "max_input_tokens": 196608, @@ -37599,6 +37636,17 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" }, + "nebius/zai-org/GLM-5.3": { + "input_cost_per_token": 1.4e-06, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/zai-org/GLM-5.3-Flash": { "max_tokens": 1024000, "max_input_tokens": 1024000, @@ -44017,6 +44065,20 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://docs.together.ai/docs/serverless-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "together_ai/deepseek-ai/DeepSeek-V4-Pro": { "deprecation_date": "2026-08-27", "cache_read_input_token_cost": 2e-07, @@ -61060,6 +61122,32 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 89d582db151..0954f9360fa 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -352,6 +352,17 @@ "supports_function_calling": true, "supports_pdf_input": true }, + "writer.palmyra-vision-7b": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "bedrock_converse", + "max_input_tokens": 4096, + "max_output_tokens": 4096, + "max_tokens": 4096, + "mode": "chat", + "output_cost_per_token": 6e-07, + "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-writer-palmyra-vision-7b.html", + "supports_vision": true + }, "amazon.nova-lite-v1:0": { "input_cost_per_token": 6e-08, "litellm_provider": "bedrock_converse", @@ -14650,6 +14661,21 @@ "supports_function_calling": true, "supports_tool_choice": true }, + "command-a-plus-05-2026": { + "input_cost_per_token": 0.0, + "litellm_provider": "cohere_chat", + "max_input_tokens": 128000, + "max_output_tokens": 64000, + "max_tokens": 64000, + "mode": "chat", + "output_cost_per_token": 0.0, + "source": "https://docs.cohere.com/docs/command-a-plus", + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true + }, "command-light": { "input_cost_per_token": 3e-07, "litellm_provider": "cohere_chat", @@ -34159,6 +34185,7 @@ "supports_tool_choice": true }, "inception/mercury-2.5": { + "cache_read_input_token_cost": 2e-08, "input_cost_per_token": 2e-07, "litellm_provider": "inception", "max_input_tokens": 260000, @@ -34168,6 +34195,7 @@ "output_cost_per_token": 7.5e-07, "source": "https://docs.inceptionlabs.ai/get-started/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true @@ -37333,6 +37361,15 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro" }, + "nebius/deepseek-ai/DeepSeek-V4-Pro-0813": { + "input_cost_per_token": 1.32e-06, + "litellm_provider": "nebius", + "mode": "chat", + "output_cost_per_token": 3.96e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/deepseek-ai%2FDeepSeek-V4-Pro-0813", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/MiniMaxAI/MiniMax-M2.5": { "max_tokens": 196608, "max_input_tokens": 196608, @@ -37599,6 +37636,17 @@ "supports_reasoning": true, "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.2" }, + "nebius/zai-org/GLM-5.3": { + "input_cost_per_token": 1.4e-06, + "litellm_provider": "nebius", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://tokenfactory.nebius.com/models/catalog/text2text/zai-org%2FGLM-5.3", + "supports_function_calling": true, + "supports_reasoning": true + }, "nebius/zai-org/GLM-5.3-Flash": { "max_tokens": 1024000, "max_input_tokens": 1024000, @@ -44017,6 +44065,20 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { + "cache_read_input_token_cost": 6e-09, + "input_cost_per_token": 3e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 1000000, + "max_tokens": 1000000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "source": "https://docs.together.ai/docs/serverless-models", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "together_ai/deepseek-ai/DeepSeek-V4-Pro": { "deprecation_date": "2026-08-27", "cache_read_input_token_cost": 2e-07, @@ -61060,6 +61122,32 @@ "supports_tool_choice": true, "supports_vision": false }, + "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, + "fireworks_ai/glm-5p3-fast": { + "cache_read_input_token_cost": 3.9e-07, + "input_cost_per_token": 2.1e-06, + "litellm_provider": "fireworks_ai", + "max_input_tokens": 1048576, + "max_tokens": 1048576, + "mode": "chat", + "output_cost_per_token": 6.6e-06, + "source": "https://docs.fireworks.ai/serverless/pricing", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": false + }, "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": { "cache_read_input_token_cost": 3e-08, "input_cost_per_token": 1.5e-07, From 2a06ece58c1f830ad4ada60832bd0df5335b1cd3 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 14 Sep 2026 19:37:25 +0000 Subject: [PATCH 02/16] feat(models): mark Fireworks GLM 5.3 Fast router as supporting reasoning and response schema Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 4 ++++ model_prices_and_context_window.json | 4 ++++ 2 files changed, 8 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 0954f9360fa..67637285862 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -61132,6 +61132,8 @@ "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, @@ -61145,6 +61147,8 @@ "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 0954f9360fa..67637285862 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -61132,6 +61132,8 @@ "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, @@ -61145,6 +61147,8 @@ "output_cost_per_token": 6.6e-06, "source": "https://docs.fireworks.ai/serverless/pricing", "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": false }, From 67382465860ecc96db6e1be3bdb68450e5223678 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Mon, 14 Sep 2026 21:26:40 +0000 Subject: [PATCH 03/16] chore(models): credit absorbed Inception Mercury 2.5 cache pricing from #41016 Co-Authored-By: Nanduu24 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> From 631ba7f9e3d1d8dc8f3bc3616ad33723e307d305 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 13:36:11 +0000 Subject: [PATCH 04/16] fix(models): dedupe merged keys, price gemini *-latest aliases at live targets, add Nova cache read prices and Fireworks deprecation dates Absorbs #41148 and #41152 into the rolling registry PR. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 338 +++++++++++------- model_prices_and_context_window.json | 338 +++++++++++------- ..._cross_region_inference_profile_mapping.py | 54 ++- .../llms/gemini/test_cost_calculator.py | 42 ++- 4 files changed, 495 insertions(+), 277 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 39370862516..d3c3cb9079b 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -376,7 +376,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.5e-08 }, "amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, @@ -558,7 +559,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 8.75e-09 }, "amazon.nova-pro-v1:0": { "input_cost_per_token": 8e-07, @@ -573,7 +575,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 2e-07 }, "amazon.nova-sonic-v1:0": { "deprecation_date": "2026-09-14", @@ -22470,7 +22473,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2026-08-27" }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, @@ -22857,7 +22861,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2026-08-27" }, "fireworks_ai/accounts/fireworks/models/minimax-m3": { "cache_read_input_token_cost": 6e-08, @@ -22963,7 +22968,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2026-08-27" }, "fireworks_ai/glm-4p7": { "cache_read_input_token_cost": 3e-07, @@ -23181,7 +23187,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2026-08-27" }, "fireworks_ai/minimax-m3": { "cache_read_input_token_cost": 6e-08, @@ -26435,13 +26442,71 @@ "supports_image_size": false }, "gemini/gemini-flash-latest": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" + }, + "gemini/gemini-flash-lite-latest": { "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -26475,58 +26540,23 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 - }, - "gemini/gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini/gemini-2.5-flash-lite-preview-06-17": { "deprecation_date": "2025-11-18", @@ -44717,7 +44747,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.5e-08 }, "us.amazon.nova-micro-v1:0": { "input_cost_per_token": 3.5e-08, @@ -44730,7 +44761,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 8.75e-09 }, "us.amazon.nova-premier-v1:0": { "deprecation_date": "2026-09-14", @@ -44743,9 +44775,10 @@ "output_cost_per_token": 1.25e-05, "supports_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 6.25e-07 }, "us.amazon.nova-pro-v1:0": { "input_cost_per_token": 8e-07, @@ -44760,7 +44793,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 2e-07 }, "us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, @@ -55684,18 +55718,17 @@ ] }, "gemini-flash-latest": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 2.5e-06, - "output_cost_per_token": 2.5e-06, + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -55724,25 +55757,37 @@ "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -55771,29 +55816,42 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -55817,29 +55875,42 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query" }, "gemini/gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -55863,11 +55934,23 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query" }, "gemini-exp-1206": { "cache_read_input_token_cost": 3e-08, @@ -58471,7 +58554,8 @@ "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_response_schema": true }, "fireworks_ai/accounts/fireworks/models/kimi-k3": { "cache_read_input_token_cost": 3e-07, @@ -65873,14 +65957,6 @@ "supports_response_schema": true, "supports_vision": false }, - "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { - "cache_read_input_token_cost": 3.9e-07, - "input_cost_per_token": 2.1e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://api.fireworks.ai/v1/serverless/models" - }, "together_ai/arcee-ai/trinity-mini": { "input_cost_per_token": 4.5e-08, "litellm_provider": "together_ai", @@ -65916,14 +65992,6 @@ "output_cost_per_token": 1.6e-06, "source": "https://api.together.ai/v1/models" }, - "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" - }, "vertex_ai/gemini-2.5-flash-native-audio": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 39370862516..d3c3cb9079b 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -376,7 +376,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.5e-08 }, "amazon.nova-2-lite-v1:0": { "cache_read_input_token_cost": 7.5e-08, @@ -558,7 +559,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 8.75e-09 }, "amazon.nova-pro-v1:0": { "input_cost_per_token": 8e-07, @@ -573,7 +575,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 2e-07 }, "amazon.nova-sonic-v1:0": { "deprecation_date": "2026-09-14", @@ -22470,7 +22473,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2026-08-27" }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, @@ -22857,7 +22861,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2026-08-27" }, "fireworks_ai/accounts/fireworks/models/minimax-m3": { "cache_read_input_token_cost": 6e-08, @@ -22963,7 +22968,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2026-08-27" }, "fireworks_ai/glm-4p7": { "cache_read_input_token_cost": 3e-07, @@ -23181,7 +23187,8 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false + "supports_vision": false, + "deprecation_date": "2026-08-27" }, "fireworks_ai/minimax-m3": { "cache_read_input_token_cost": 6e-08, @@ -26435,13 +26442,71 @@ "supports_image_size": false }, "gemini/gemini-flash-latest": { + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 1048576, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, + "rpm": 15, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/completions", + "/v1/batch" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_audio_output": false, + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_url_context": true, + "supports_vision": true, + "supports_web_search": true, + "tpm": 250000, + "search_context_cost_per_query": { + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 + }, + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" + }, + "gemini/gemini-flash-lite-latest": { "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 1e-06, "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 2.5e-06, "output_cost_per_token": 2.5e-06, @@ -26475,58 +26540,23 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 - }, - "gemini/gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, - "litellm_provider": "gemini", - "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, - "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, - "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/chat/completions", - "/v1/completions", - "/v1/batch" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text" - ], - "supports_audio_output": false, - "supports_function_calling": true, - "supports_parallel_function_calling": true, - "supports_pdf_input": true, - "supports_prompt_caching": true, - "supports_reasoning": true, - "supports_response_schema": true, - "supports_system_messages": true, - "supports_tool_choice": true, - "supports_url_context": true, - "supports_vision": true, - "supports_web_search": true, - "tpm": 250000, - "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 - }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini/gemini-2.5-flash-lite-preview-06-17": { "deprecation_date": "2025-11-18", @@ -44717,7 +44747,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 1.5e-08 }, "us.amazon.nova-micro-v1:0": { "input_cost_per_token": 3.5e-08, @@ -44730,7 +44761,8 @@ "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 8.75e-09 }, "us.amazon.nova-premier-v1:0": { "deprecation_date": "2026-09-14", @@ -44743,9 +44775,10 @@ "output_cost_per_token": 1.25e-05, "supports_function_calling": true, "supports_pdf_input": true, - "supports_prompt_caching": false, + "supports_prompt_caching": true, "supports_response_schema": true, - "supports_vision": true + "supports_vision": true, + "cache_read_input_token_cost": 6.25e-07 }, "us.amazon.nova-pro-v1:0": { "input_cost_per_token": 8e-07, @@ -44760,7 +44793,8 @@ "supports_prompt_caching": true, "supports_response_schema": true, "supports_vision": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "cache_read_input_token_cost": 2e-07 }, "us.anthropic.claude-3-5-haiku-20241022-v1:0": { "cache_creation_input_token_cost": 1e-06, @@ -55684,18 +55718,17 @@ ] }, "gemini-flash-latest": { - "cache_read_input_token_cost": 3e-08, - "input_cost_per_audio_token": 1e-06, - "input_cost_per_token": 3e-07, + "cache_read_input_token_cost": 7.5e-08, + "input_cost_per_token": 7.5e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 2.5e-06, - "output_cost_per_token": 2.5e-06, + "output_cost_per_reasoning_token": 3.75e-06, + "output_cost_per_token": 3.75e-06, "rpm": 100000, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -55724,25 +55757,37 @@ "supports_web_search": true, "tpm": 8000000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 3.75e-08, + "cache_read_input_token_cost_priority": 1.35e-07, + "input_cost_per_token_batches": 3.75e-07, + "input_cost_per_token_flex": 3.75e-07, + "input_cost_per_token_priority": 1.35e-06, + "output_cost_per_token_batches": 1.875e-06, + "output_cost_per_token_flex": 1.875e-06, + "output_cost_per_token_priority": 6.75e-06, + "prompt_cache_min_tokens": 4096, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-flash-lite-latest": { - "cache_read_input_token_cost": 1e-08, - "input_cost_per_audio_token": 3e-07, - "input_cost_per_token": 1e-07, + "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 3e-07, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_reasoning_token": 4e-07, - "output_cost_per_token": 4e-07, + "output_cost_per_reasoning_token": 2.5e-06, + "output_cost_per_token": 2.5e-06, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-lite", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -55771,29 +55816,42 @@ "supports_web_search": true, "tpm": 250000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_flex": 2e-08, + "cache_read_input_token_cost_priority": 5e-08, + "input_cost_per_token_batches": 1.5e-07, + "input_cost_per_token_flex": 1.5e-07, + "input_cost_per_token_priority": 5.4e-07, + "output_cost_per_token_batches": 1.25e-06, + "output_cost_per_token_flex": 1.25e-06, + "output_cost_per_token_priority": 4.5e-06, + "supports_audio_input": true, + "supports_native_streaming": true, + "supports_video_input": true, + "web_search_billing_unit": "per_query" }, "gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -55817,29 +55875,42 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query" }, "gemini/gemini-pro-latest": { - "cache_read_input_token_cost": 1.25e-07, - "cache_read_input_token_cost_above_200k_tokens": 2.5e-07, - "input_cost_per_token": 1.25e-06, - "input_cost_per_token_above_200k_tokens": 2.5e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_200k_tokens": 4e-07, + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_200k_tokens": 4e-06, "litellm_provider": "gemini", "max_input_tokens": 1048576, - "max_output_tokens": 65535, - "max_tokens": 65535, + "max_output_tokens": 65536, + "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1e-05, - "output_cost_per_token_above_200k_tokens": 1.5e-05, + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_200k_tokens": 1.8e-05, "rpm": 2000, - "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing", "supported_endpoints": [ "/v1/chat/completions", - "/v1/completions" + "/v1/completions", + "/v1/batch" ], "supported_modalities": [ "text", @@ -55863,11 +55934,23 @@ "supports_web_search": true, "tpm": 800000, "search_context_cost_per_query": { - "search_context_size_low": 0.035, - "search_context_size_medium": 0.035, - "search_context_size_high": 0.035 + "search_context_size_low": 0.014, + "search_context_size_medium": 0.014, + "search_context_size_high": 0.014 }, - "google_maps_grounding_cost_per_query": 0.025 + "google_maps_grounding_cost_per_query": 0.014, + "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07, + "cache_read_input_token_cost_priority": 3.6e-07, + "input_cost_per_token_above_200k_tokens_priority": 7.2e-06, + "input_cost_per_token_batches": 1e-06, + "input_cost_per_token_priority": 3.6e-06, + "output_cost_per_token_above_200k_tokens_priority": 3.24e-05, + "output_cost_per_token_batches": 6e-06, + "output_cost_per_token_priority": 2.16e-05, + "prompt_cache_min_tokens": 4096, + "supports_native_streaming": true, + "supports_url_context": true, + "web_search_billing_unit": "per_query" }, "gemini-exp-1206": { "cache_read_input_token_cost": 3e-08, @@ -58471,7 +58554,8 @@ "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_response_schema": true }, "fireworks_ai/accounts/fireworks/models/kimi-k3": { "cache_read_input_token_cost": 3e-07, @@ -65873,14 +65957,6 @@ "supports_response_schema": true, "supports_vision": false }, - "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": { - "cache_read_input_token_cost": 3.9e-07, - "input_cost_per_token": 2.1e-06, - "litellm_provider": "fireworks_ai", - "mode": "chat", - "output_cost_per_token": 6.6e-06, - "source": "https://api.fireworks.ai/v1/serverless/models" - }, "together_ai/arcee-ai/trinity-mini": { "input_cost_per_token": 4.5e-08, "litellm_provider": "together_ai", @@ -65916,14 +65992,6 @@ "output_cost_per_token": 1.6e-06, "source": "https://api.together.ai/v1/models" }, - "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": { - "cache_read_input_token_cost": 6e-09, - "input_cost_per_token": 3e-07, - "litellm_provider": "together_ai", - "mode": "chat", - "output_cost_per_token": 1.2e-06, - "source": "https://api.together.ai/v1/models" - }, "vertex_ai/gemini-2.5-flash-native-audio": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, diff --git a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py index fda3c8ceb8f..b567a8669b4 100644 --- a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py +++ b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py @@ -4,12 +4,10 @@ from typing import NamedTuple import pytest - import litellm +from litellm.cost_calculator import completion_cost from litellm.llms.bedrock.chat.converse_transformation import AmazonConverseConfig from litellm.llms.bedrock.common_utils import BedrockModelInfo -from litellm.utils import _get_model_info_helper -from litellm.cost_calculator import completion_cost from litellm.types.utils import ( Choices, Message, @@ -17,6 +15,7 @@ from litellm.types.utils import ( PromptTokensDetailsWrapper, Usage, ) +from litellm.utils import _get_model_info_helper @pytest.fixture @@ -228,3 +227,52 @@ def test_bedrock_gpt_5_6_offers_tools_and_reasoning_effort_but_not_thinking(prof assert "reasoning_effort" in supported assert "thinking" not in supported assert "output_config" not in supported + + +@pytest.mark.parametrize( + "model,expected_cache_read", + [ + ("amazon.nova-lite-v1:0", 1.5e-8), + ("us.amazon.nova-lite-v1:0", 1.5e-8), + ("amazon.nova-micro-v1:0", 8.75e-9), + ("us.amazon.nova-micro-v1:0", 8.75e-9), + ("amazon.nova-pro-v1:0", 2e-7), + ("us.amazon.nova-pro-v1:0", 2e-7), + ("us.amazon.nova-premier-v1:0", 6.25e-7), + ], +) +def test_bedrock_nova_cache_read_prices( + model, expected_cache_read, local_model_cost_map +): + model_info = litellm.model_cost[model] + usage = Usage( + prompt_tokens=1_000, + completion_tokens=100, + total_tokens=1_100, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=400), + ) + response = _bedrock_response(model, usage) + + cost = completion_cost( + completion_response=response, + model=model, + custom_llm_provider="bedrock", + ) + expected_cost = ( + 600 * model_info["input_cost_per_token"] + + 400 * expected_cache_read + + 100 * model_info["output_cost_per_token"] + ) + assert cost == pytest.approx(expected_cost) + + uncached_usage = Usage( + prompt_tokens=1_000, + completion_tokens=100, + total_tokens=1_100, + ) + uncached_cost = completion_cost( + completion_response=_bedrock_response(model, uncached_usage), + model=model, + custom_llm_provider="bedrock", + ) + assert cost < uncached_cost diff --git a/tests/test_litellm/llms/gemini/test_cost_calculator.py b/tests/test_litellm/llms/gemini/test_cost_calculator.py index 6d547b0dc55..85d62030c00 100644 --- a/tests/test_litellm/llms/gemini/test_cost_calculator.py +++ b/tests/test_litellm/llms/gemini/test_cost_calculator.py @@ -1,8 +1,7 @@ -import os - import pytest import litellm +from litellm.cost_calculator import completion_cost from litellm.llms.gemini.cost_calculator import ( cost_per_google_maps_grounding_request, cost_per_web_search_request, @@ -18,6 +17,7 @@ from litellm.types.utils import ( ImageResponse, ImageUsage, ImageUsageInputTokensDetails, + ModelResponse, PromptTokensDetailsWrapper, Usage, ) @@ -455,8 +455,8 @@ def test_map_traffic_type_to_service_tier( @pytest.mark.parametrize( "model,custom_llm_provider,expected_cache_read_cost", [ - ("gemini/gemini-flash-latest", "gemini", 3e-08), - ("gemini/gemini-flash-lite-latest", "gemini", 1e-08), + ("gemini/gemini-flash-latest", "gemini", 7.5e-08), + ("gemini/gemini-flash-lite-latest", "gemini", 3e-08), ("gemini/gemini-2.5-flash-preview-09-2025", "gemini", 3e-08), ("gemini/gemini-2.5-flash-lite-preview-06-17", "gemini", 1e-08), ("vertex_ai/gemini-2.5-flash-preview-09-2025", "vertex_ai", 3e-08), @@ -479,6 +479,40 @@ def test_flash_alias_cache_read_is_ten_percent_of_input( ) +@pytest.mark.parametrize( + "alias,target", + [ + ("gemini/gemini-flash-latest", "gemini/gemini-3.8-flash"), + ("gemini/gemini-flash-lite-latest", "gemini/gemini-3.5-flash-lite"), + ("gemini/gemini-pro-latest", "gemini/gemini-3.1-pro-preview"), + ], +) +def test_latest_aliases_cost_the_same_as_their_current_target( + monkeypatch, alias, target +): + monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True") + monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url="")) + + usage = Usage( + prompt_tokens=1_000, + completion_tokens=500, + total_tokens=1_500, + prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=400), + ) + + def cost_of(model: str) -> float: + return completion_cost( + completion_response=ModelResponse(model=model, usage=usage), + model=model, + custom_llm_provider="gemini", + ) + + alias_cost = cost_of(alias) + target_cost = cost_of(target) + assert alias_cost == pytest.approx(target_cost) + assert alias_cost > 0 + + @pytest.mark.parametrize( "prefixed,bare", [ From 3000c00c502d4d662ba369b2fa3bd628f73b9cc8 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 14:03:24 +0000 Subject: [PATCH 05/16] fix(models): add supports_response_schema to fireworks deepseek-v4-flash-vision-exp short alias Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 3 ++- model_prices_and_context_window.json | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index d3c3cb9079b..e2c9a3edb87 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -58631,7 +58631,8 @@ "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_response_schema": true }, "fireworks_ai/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index d3c3cb9079b..e2c9a3edb87 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -58631,7 +58631,8 @@ "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_response_schema": true }, "fireworks_ai/glm-5p2-fast": { "cache_read_input_token_cost": 2.1e-07, From 93f27d6082f235bb7c264abad0006038d16b321d Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 19:15:46 +0000 Subject: [PATCH 06/16] fix(registry): add gemini 3.8 live, azure gpt-5.5/luna snapshots, doubao seed 2.1, fix together v4.1 flash context Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 425 +++++++++++++++++- model_prices_and_context_window.json | 425 +++++++++++++++++- 2 files changed, 844 insertions(+), 6 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e2c9a3edb87..ce531ba1fe1 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3781,6 +3781,53 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure_ai/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure_ai/gpt-5.4": { "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, @@ -7380,6 +7427,62 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-luna-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_priority": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_priority": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_priority": 4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_priority": 2.4e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, @@ -8218,6 +8321,58 @@ "supports_web_search": true, "deprecation_date": "2027-10-26" }, + "azure/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, @@ -8263,6 +8418,55 @@ "supports_web_search": true, "deprecation_date": "2027-10-26" }, + "azure/us/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.38e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, @@ -8308,6 +8512,55 @@ "supports_web_search": true, "deprecation_date": "2027-10-26" }, + "azure/eu/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.38e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, @@ -44436,11 +44689,11 @@ "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", - "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_input_tokens": 1048576, + "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.xyz/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -55573,6 +55826,73 @@ "supports_web_search": true, "gemini_audio_only_live": true }, + "gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true + }, + "gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true, + "supports_reasoning": true + }, "gemini/gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, @@ -55692,6 +56012,73 @@ "rpm": 10, "gemini_audio_only_live": true }, + "gemini/gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true + }, + "gemini/gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true, + "supports_reasoning": true + }, "gemini/gemini-3.1-flash-tts-preview": { "input_cost_per_token": 1e-06, "litellm_provider": "gemini", @@ -56850,6 +57237,38 @@ } ] }, + "volcengine/doubao-seed-2-1-pro-260628": { + "cache_read_input_token_cost": 1.725e-07, + "input_cost_per_token": 8.625e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4.3125e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-turbo-260628": { + "cache_read_input_token_cost": 8.625e-08, + "input_cost_per_token": 4.3125e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.15625e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, "volcengine/doubao-seed-2-0-lite-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e2c9a3edb87..ce531ba1fe1 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3781,6 +3781,53 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure_ai/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure_ai", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure_ai/gpt-5.4": { "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 2.5e-07, @@ -7380,6 +7427,62 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-luna-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-07, + "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_priority": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_read_input_token_cost": 2e-08, + "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_priority": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-07, + "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_priority": 4e-07, + "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-06, + "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_priority": 2.4e-06, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, @@ -8218,6 +8321,58 @@ "supports_web_search": true, "deprecation_date": "2027-10-26" }, + "azure/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1e-06, + "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_token_above_272k_tokens": 1e-05, + "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 3e-05, + "output_cost_per_token_above_272k_tokens": 4.5e-05, + "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_above_272k_tokens_priority": 9e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, @@ -8263,6 +8418,55 @@ "supports_web_search": true, "deprecation_date": "2027-10-26" }, + "azure/us/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.38e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, @@ -8308,6 +8512,55 @@ "supports_web_search": true, "deprecation_date": "2027-10-26" }, + "azure/eu/gpt-5.5-2026-04-24": { + "deprecation_date": "2027-10-26", + "cache_read_input_token_cost": 5.5e-07, + "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, + "cache_read_input_token_cost_priority": 1.38e-06, + "input_cost_per_token": 5.5e-06, + "input_cost_per_token_above_272k_tokens": 1.1e-05, + "input_cost_per_token_priority": 1.375e-05, + "output_cost_per_token": 3.3e-05, + "output_cost_per_token_above_272k_tokens": 4.95e-05, + "output_cost_per_token_priority": 8.25e-05, + "litellm_provider": "azure", + "max_input_tokens": 1050000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, "cache_read_input_token_cost_above_272k_tokens": 6e-06, @@ -44436,11 +44689,11 @@ "cache_read_input_token_cost": 6e-09, "input_cost_per_token": 3e-07, "litellm_provider": "together_ai", - "max_input_tokens": 1000000, - "max_tokens": 1000000, + "max_input_tokens": 1048576, + "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://docs.together.ai/docs/serverless-models", + "source": "https://api.together.xyz/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -55573,6 +55826,73 @@ "supports_web_search": true, "gemini_audio_only_live": true }, + "gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true + }, + "gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true, + "supports_reasoning": true + }, "gemini/gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, "input_cost_per_token": 5e-07, @@ -55692,6 +56012,73 @@ "rpm": 10, "gemini_audio_only_live": true }, + "gemini/gemini-3.8-live": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true + }, + "gemini/gemini-3.8-live-extended-thinking": { + "input_cost_per_audio_token": 3e-06, + "input_cost_per_image_token": 1e-06, + "input_cost_per_token": 7.5e-07, + "input_cost_per_video_per_second": 3.3333333333333335e-05, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "max_tokens": 65536, + "mode": "realtime", + "output_cost_per_audio_token": 1.2e-05, + "output_cost_per_token": 4.5e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1/realtime" + ], + "supported_modalities": [ + "text", + "image", + "audio", + "video" + ], + "supported_output_modalities": [ + "text", + "audio" + ], + "supports_audio_input": true, + "supports_audio_output": true, + "supports_function_calling": true, + "supports_vision": true, + "supports_web_search": true, + "gemini_audio_only_live": true, + "supports_reasoning": true + }, "gemini/gemini-3.1-flash-tts-preview": { "input_cost_per_token": 1e-06, "litellm_provider": "gemini", @@ -56850,6 +57237,38 @@ } ] }, + "volcengine/doubao-seed-2-1-pro-260628": { + "cache_read_input_token_cost": 1.725e-07, + "input_cost_per_token": 8.625e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 4.3125e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, + "volcengine/doubao-seed-2-1-turbo-260628": { + "cache_read_input_token_cost": 8.625e-08, + "input_cost_per_token": 4.3125e-07, + "litellm_provider": "volcengine", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.15625e-06, + "source": "https://www.volcengine.com/docs/82379/1544106", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_tool_choice": false, + "supports_vision": true + }, "volcengine/doubao-seed-2-0-lite-260215": { "litellm_provider": "volcengine", "max_input_tokens": 256000, From 11211cbf29087a5eb474dd708e04a9910494ddd3 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 20:18:29 +0000 Subject: [PATCH 07/16] fix(registry): drop gemini/gemini-3.8-live entries pending published rate limits The gemini/ realtime test requires tpm and rpm, and Google publishes the Live model limits only behind the AI Studio login, so the direct-API keys cannot be sourced yet. The Vertex keys stay. Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 67 ------------------- model_prices_and_context_window.json | 67 ------------------- 2 files changed, 134 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index ce531ba1fe1..5631220144e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -56012,73 +56012,6 @@ "rpm": 10, "gemini_audio_only_live": true }, - "gemini/gemini-3.8-live": { - "input_cost_per_audio_token": 3e-06, - "input_cost_per_image_token": 1e-06, - "input_cost_per_token": 7.5e-07, - "input_cost_per_video_per_second": 3.3333333333333335e-05, - "litellm_provider": "gemini", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "realtime", - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_web_search": true, - "gemini_audio_only_live": true - }, - "gemini/gemini-3.8-live-extended-thinking": { - "input_cost_per_audio_token": 3e-06, - "input_cost_per_image_token": 1e-06, - "input_cost_per_token": 7.5e-07, - "input_cost_per_video_per_second": 3.3333333333333335e-05, - "litellm_provider": "gemini", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "realtime", - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_web_search": true, - "gemini_audio_only_live": true, - "supports_reasoning": true - }, "gemini/gemini-3.1-flash-tts-preview": { "input_cost_per_token": 1e-06, "litellm_provider": "gemini", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index ce531ba1fe1..5631220144e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -56012,73 +56012,6 @@ "rpm": 10, "gemini_audio_only_live": true }, - "gemini/gemini-3.8-live": { - "input_cost_per_audio_token": 3e-06, - "input_cost_per_image_token": 1e-06, - "input_cost_per_token": 7.5e-07, - "input_cost_per_video_per_second": 3.3333333333333335e-05, - "litellm_provider": "gemini", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "realtime", - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_web_search": true, - "gemini_audio_only_live": true - }, - "gemini/gemini-3.8-live-extended-thinking": { - "input_cost_per_audio_token": 3e-06, - "input_cost_per_image_token": 1e-06, - "input_cost_per_token": 7.5e-07, - "input_cost_per_video_per_second": 3.3333333333333335e-05, - "litellm_provider": "gemini", - "max_input_tokens": 131072, - "max_output_tokens": 65536, - "max_tokens": 65536, - "mode": "realtime", - "output_cost_per_audio_token": 1.2e-05, - "output_cost_per_token": 4.5e-06, - "source": "https://ai.google.dev/gemini-api/docs/pricing", - "supported_endpoints": [ - "/v1/realtime" - ], - "supported_modalities": [ - "text", - "image", - "audio", - "video" - ], - "supported_output_modalities": [ - "text", - "audio" - ], - "supports_audio_input": true, - "supports_audio_output": true, - "supports_function_calling": true, - "supports_vision": true, - "supports_web_search": true, - "gemini_audio_only_live": true, - "supports_reasoning": true - }, "gemini/gemini-3.1-flash-tts-preview": { "input_cost_per_token": 1e-06, "litellm_provider": "gemini", From 65a2e4f5039449c64c66507a8c63967c00004d0e Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 20:38:52 +0000 Subject: [PATCH 08/16] test(cost): derive Nova cache expectations from registry and cite Gemini alias targets Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ..._cross_region_inference_profile_mapping.py | 22 +++++++++---------- .../llms/gemini/test_cost_calculator.py | 2 ++ 2 files changed, 13 insertions(+), 11 deletions(-) diff --git a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py index b567a8669b4..b12ca31c694 100644 --- a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py +++ b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py @@ -230,21 +230,21 @@ def test_bedrock_gpt_5_6_offers_tools_and_reasoning_effort_but_not_thinking(prof @pytest.mark.parametrize( - "model,expected_cache_read", + "model", [ - ("amazon.nova-lite-v1:0", 1.5e-8), - ("us.amazon.nova-lite-v1:0", 1.5e-8), - ("amazon.nova-micro-v1:0", 8.75e-9), - ("us.amazon.nova-micro-v1:0", 8.75e-9), - ("amazon.nova-pro-v1:0", 2e-7), - ("us.amazon.nova-pro-v1:0", 2e-7), - ("us.amazon.nova-premier-v1:0", 6.25e-7), + "amazon.nova-lite-v1:0", + "us.amazon.nova-lite-v1:0", + "amazon.nova-micro-v1:0", + "us.amazon.nova-micro-v1:0", + "amazon.nova-pro-v1:0", + "us.amazon.nova-pro-v1:0", + "us.amazon.nova-premier-v1:0", ], ) -def test_bedrock_nova_cache_read_prices( - model, expected_cache_read, local_model_cost_map -): +def test_bedrock_nova_cache_read_prices(model, local_model_cost_map): model_info = litellm.model_cost[model] + expected_cache_read = model_info["cache_read_input_token_cost"] + assert 0 < expected_cache_read < model_info["input_cost_per_token"] usage = Usage( prompt_tokens=1_000, completion_tokens=100, diff --git a/tests/test_litellm/llms/gemini/test_cost_calculator.py b/tests/test_litellm/llms/gemini/test_cost_calculator.py index 8ad27411ce3..5eed11dff03 100644 --- a/tests/test_litellm/llms/gemini/test_cost_calculator.py +++ b/tests/test_litellm/llms/gemini/test_cost_calculator.py @@ -452,6 +452,8 @@ def test_map_traffic_type_to_service_tier( ) +# Alias targets are the `modelVersion` returned by +# POST https://generativelanguage.googleapis.com/v1beta/models/:generateContent on 2026-09-15 @pytest.mark.parametrize( "alias,target", [ From 5f0934309918b2b65c39c65f5eae3d1321e9ca3c Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Tue, 15 Sep 2026 20:50:01 +0000 Subject: [PATCH 09/16] test(bedrock): pin Nova cache-read prices with dated AWS Price List citation Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ..._cross_region_inference_profile_mapping.py | 25 +++++++++++-------- 1 file changed, 14 insertions(+), 11 deletions(-) diff --git a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py index b12ca31c694..b1e85c4f5ea 100644 --- a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py +++ b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py @@ -229,22 +229,25 @@ def test_bedrock_gpt_5_6_offers_tools_and_reasoning_effort_but_not_thinking(prof assert "output_config" not in supported +# Cache-read prices are the `*-cache-read-input-tokens` usagetype rows of the AWS Price List API, us-east-1, +# https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/us-east-1/index.json on 2026-09-15 @pytest.mark.parametrize( - "model", + "model,expected_cache_read", [ - "amazon.nova-lite-v1:0", - "us.amazon.nova-lite-v1:0", - "amazon.nova-micro-v1:0", - "us.amazon.nova-micro-v1:0", - "amazon.nova-pro-v1:0", - "us.amazon.nova-pro-v1:0", - "us.amazon.nova-premier-v1:0", + ("amazon.nova-lite-v1:0", 1.5e-8), + ("us.amazon.nova-lite-v1:0", 1.5e-8), + ("amazon.nova-micro-v1:0", 8.75e-9), + ("us.amazon.nova-micro-v1:0", 8.75e-9), + ("amazon.nova-pro-v1:0", 2e-7), + ("us.amazon.nova-pro-v1:0", 2e-7), + ("us.amazon.nova-premier-v1:0", 6.25e-7), ], ) -def test_bedrock_nova_cache_read_prices(model, local_model_cost_map): +def test_bedrock_nova_cache_read_prices( + model, expected_cache_read, local_model_cost_map +): model_info = litellm.model_cost[model] - expected_cache_read = model_info["cache_read_input_token_cost"] - assert 0 < expected_cache_read < model_info["input_cost_per_token"] + assert model_info["cache_read_input_token_cost"] == expected_cache_read usage = Usage( prompt_tokens=1_000, completion_tokens=100, From 642525f5712b50c9847eecf17c32d39152d50b8f Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 13:19:53 +0000 Subject: [PATCH 10/16] fix(registry): add azure gpt-image-2.5 entries and together/azure deprecation dates Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 53 +++++++++++++++++-- model_prices_and_context_window.json | 53 +++++++++++++++++-- 2 files changed, 98 insertions(+), 8 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index eafbb8b1048..542a1113112 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -5265,6 +5265,7 @@ "supports_vision": true }, "azure/gpt-4o": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -8988,6 +8989,36 @@ "supports_vision": true, "supports_pdf_input": true }, + "azure/gpt-image-2.5-flare": { + "deprecation_date": "2027-09-09", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "azure/gpt-image-2.5-sunburst": { + "deprecation_date": "2027-09-09", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, "azure/gpt-image-2-2026-04-21": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", @@ -44437,7 +44468,7 @@ "supports_tool_choice": true }, "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -44744,7 +44775,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -44759,7 +44790,7 @@ "supports_vision": true }, "together_ai/intfloat/multilingual-e5-large-instruct": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "max_input_tokens": 514, @@ -44872,7 +44903,7 @@ "supports_tool_choice": true }, "together_ai/thinkingmachines/Inkling-Small": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", @@ -66337,6 +66368,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { + "deprecation_date": "2024-08-22", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66344,6 +66376,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66351,6 +66384,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66358,6 +66392,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 1.6e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66443,6 +66478,7 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "together_ai/google/gemma-2-27b-it": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66467,6 +66503,7 @@ "source": "https://developers.openai.com/api/docs/pricing" }, "together_ai/meta-llama/Llama-3-8b-chat-hf": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66495,6 +66532,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66502,6 +66540,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66509,6 +66548,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66516,6 +66556,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66530,6 +66571,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 9e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66537,6 +66579,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-VL-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66558,6 +66601,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66565,6 +66609,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { + "deprecation_date": "2026-01-05", "input_cost_per_token": 1.95e-06, "litellm_provider": "together_ai", "mode": "chat", diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index eafbb8b1048..542a1113112 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -5265,6 +5265,7 @@ "supports_vision": true }, "azure/gpt-4o": { + "deprecation_date": "2027-04-14", "cache_read_input_token_cost": 1.25e-06, "input_cost_per_token": 2.5e-06, "litellm_provider": "azure", @@ -8988,6 +8989,36 @@ "supports_vision": true, "supports_pdf_input": true }, + "azure/gpt-image-2.5-flare": { + "deprecation_date": "2027-09-09", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, + "azure/gpt-image-2.5-sunburst": { + "deprecation_date": "2027-09-09", + "cache_read_input_token_cost": 1.25e-06, + "input_cost_per_token": 5e-06, + "input_cost_per_image_token": 8e-06, + "litellm_provider": "azure", + "mode": "image_generation", + "output_cost_per_image_token": 3e-05, + "supported_endpoints": [ + "/v1/images/generations", + "/v1/images/edits" + ], + "supports_vision": true, + "supports_pdf_input": true + }, "azure/gpt-image-2-2026-04-21": { "cache_read_input_token_cost": 1.25e-06, "deprecation_date": "2027-10-21", @@ -44437,7 +44468,7 @@ "supports_tool_choice": true }, "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -44744,7 +44775,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -44759,7 +44790,7 @@ "supports_vision": true }, "together_ai/intfloat/multilingual-e5-large-instruct": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "max_input_tokens": 514, @@ -44872,7 +44903,7 @@ "supports_tool_choice": true }, "together_ai/thinkingmachines/Inkling-Small": { - "deprecation_date": "2026-09-14", + "deprecation_date": "2026-09-15", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", @@ -66337,6 +66368,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/deepseek-coder-33b-instruct": { + "deprecation_date": "2024-08-22", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66344,6 +66376,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66351,6 +66384,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66358,6 +66392,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 1.6e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66443,6 +66478,7 @@ "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing" }, "together_ai/google/gemma-2-27b-it": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66467,6 +66503,7 @@ "source": "https://developers.openai.com/api/docs/pricing" }, "together_ai/meta-llama/Llama-3-8b-chat-hf": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66495,6 +66532,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": { + "deprecation_date": "2025-12-23", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66502,6 +66540,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66509,6 +66548,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 6e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66516,6 +66556,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 8.8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66530,6 +66571,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 9e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66537,6 +66579,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2-VL-72B-Instruct": { + "deprecation_date": "2025-08-28", "input_cost_per_token": 1.2e-06, "litellm_provider": "together_ai", "mode": "chat", @@ -66558,6 +66601,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": { + "deprecation_date": "2025-11-13", "input_cost_per_token": 8e-07, "litellm_provider": "together_ai", "mode": "chat", @@ -66565,6 +66609,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": { + "deprecation_date": "2026-01-05", "input_cost_per_token": 1.95e-06, "litellm_provider": "together_ai", "mode": "chat", From ba820783acc17406aa6ffa50ea53c64e68d0ed6a Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 13:25:14 +0000 Subject: [PATCH 11/16] fix(tests): import Bedrock usage types Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../bedrock/test_cross_region_inference_profile_mapping.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py index 65e38c148be..5795e29a8bc 100644 --- a/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py +++ b/tests/test_litellm/llms/bedrock/test_cross_region_inference_profile_mapping.py @@ -12,8 +12,9 @@ from litellm.types.utils import ( Choices, Message, ModelResponse, + PromptTokensDetailsWrapper, + Usage, ) -from litellm.utils import _get_model_info_helper @pytest.fixture From 7734e3e186cb9194db22c6a4975c664a40b5a685 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 19:17:13 +0000 Subject: [PATCH 12/16] fix(models): sonnet 4.5 1M input, daybreak alias, Mistral GLM 5.3, Azure dated snapshots, Together/OpenRouter sync Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 337 +++++++++++++++--- model_prices_and_context_window.json | 337 +++++++++++++++--- 2 files changed, 568 insertions(+), 106 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 7feef3be8ea..231169b4c9f 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -7566,6 +7566,70 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-sol-2026-07-09": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_flex": 2e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_flex": 2e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "output_cost_per_token_flex": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, @@ -7630,6 +7694,70 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-terra-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_read_input_token_cost_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_flex": 1e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_flex": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, + "output_cost_per_token_priority": 2.4e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, + "output_cost_per_token_flex": 6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, @@ -7798,6 +7926,54 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/gpt-6-astra-2026-09-03": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, "deprecation_date": "2026-12-02", @@ -14186,7 +14362,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -14221,7 +14397,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -14242,7 +14418,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.anthropic.com/en/docs/about-claude/pricing" }, "claude-sonnet-5": { "deprecation_date": "2027-06-30", @@ -32459,7 +32636,7 @@ "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -32498,7 +32675,7 @@ "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -36833,6 +37010,57 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/zai-glm-5-3": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-5": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-latest": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "mistral/glm-5-2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -40578,15 +40806,16 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 3.2e-07, + "input_cost_per_token": 2.574e-07, "litellm_provider": "openrouter", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 8.9e-07, + "output_cost_per_token": 1.0287e-06, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/deepseek/deepseek-chat-v3-0324": { "input_cost_per_token": 2.5e-07, @@ -40679,21 +40908,21 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 8.59908e-07, + "input_cost_per_token": 1.6e-06, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.719816e-06, + "output_cost_per_token": 3.2e-06, "source": "https://openrouter.ai/deepseek/deepseek-v4-pro", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "cache_read_input_token_cost": 7.1659e-08 + "cache_read_input_token_cost": 1.35e-07 }, "openrouter/deepseek/deepseek-v4.1-flash": { "input_cost_per_token": 1.5e-07, @@ -40988,12 +41217,13 @@ "supports_vision": true }, "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 6e-08, + "input_cost_per_token": 8e-08, "litellm_provider": "openrouter", "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-08, - "supports_tool_choice": true + "output_cost_per_token": 1.1e-07, + "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/mancer/weaver": { "input_cost_per_token": 4e-07, @@ -41129,14 +41359,15 @@ "max_output_tokens": 131072 }, "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 7.5e-08, + "input_cost_per_token": 9.375e-08, "litellm_provider": "openrouter", "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-07, + "output_cost_per_token": 2.5e-07, "supports_tool_choice": true, "max_input_tokens": 128000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/mistralai/mixtral-8x22b-instruct": { "input_cost_per_token": 2e-06, @@ -41657,13 +41888,13 @@ "supports_tool_choice": true }, "openrouter/qwen/qwen3-235b-a22b-2507": { - "input_cost_per_token": 2.2e-07, + "input_cost_per_token": 8.75e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 8.8e-07, + "output_cost_per_token": 3.5e-07, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", "supports_function_calling": true, "supports_tool_choice": true @@ -41696,13 +41927,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-35b-a3b": { - "input_cost_per_token": 3.125e-07, + "input_cost_per_token": 1.625e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.25e-06, + "output_cost_per_token": 1.3e-06, "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", "supports_function_calling": true, "supports_reasoning": true, @@ -44718,7 +44949,7 @@ "deprecation_date": "2026-06-04", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", - "max_input_tokens": 256000, + "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models", @@ -44788,7 +45019,7 @@ "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 16384 }, "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { @@ -44971,7 +45202,7 @@ "deprecation_date": "2026-04-02", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.1e-06, "source": "https://api.together.ai/v1/models", @@ -64723,9 +64954,9 @@ "supports_prompt_caching": true }, "openrouter/z-ai/glm-5.3-flash": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 5e-07, - "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 1.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 131072, @@ -64775,9 +65006,9 @@ "supports_prompt_caching": true }, "openrouter/qwen/qwen3.8-27b": { - "input_cost_per_token": 4.2e-07, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 8.5e-08, + "input_cost_per_token": 2.14e-07, + "output_cost_per_token": 2.55e-06, + "cache_read_input_token_cost": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 131072, @@ -64860,9 +65091,9 @@ "supports_prompt_caching": true }, "openrouter/deepseek/deepseek-v4-flash-0731": { - "input_cost_per_token": 6.5e-08, - "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.2e-07, + "cache_read_input_token_cost": 1.2e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, @@ -64930,9 +65161,9 @@ "supports_vision": false }, "openrouter/moonshotai/kimi-k3": { - "input_cost_per_token": 2.1e-06, - "output_cost_per_token": 1.053e-05, - "cache_read_input_token_cost": 2.35e-07, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 943718, @@ -65029,9 +65260,9 @@ "supports_prompt_caching": true }, "openrouter/z-ai/glm-5.2": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 131072, @@ -65062,9 +65293,9 @@ "supports_vision": false }, "openrouter/moonshotai/kimi-k2.7-code": { - "input_cost_per_token": 7.1e-07, - "output_cost_per_token": 3.5e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 7.062e-07, + "output_cost_per_token": 3.21e-06, + "cache_read_input_token_cost": 1.8e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 235929, @@ -65366,8 +65597,8 @@ "supports_prompt_caching": true }, "openrouter/google/gemma-4-26b-a4b-it": { - "input_cost_per_token": 4.2e-08, - "output_cost_per_token": 2.2e-07, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 16384, @@ -65914,8 +66145,8 @@ "supports_vision": true }, "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 5.2e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 16384, @@ -66175,8 +66406,8 @@ "supports_vision": false }, "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 4.815e-08, + "output_cost_per_token": 1.9305e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 32000, @@ -66235,7 +66466,7 @@ "supports_vision": false }, "openrouter/minimax/minimax-m1": { - "input_cost_per_token": 5.5e-07, + "input_cost_per_token": 4e-07, "output_cost_per_token": 2.2e-06, "litellm_provider": "openrouter", "max_input_tokens": 1000000, @@ -66374,8 +66605,8 @@ "supports_vision": false }, "openrouter/qwen/qwen3-14b": { - "input_cost_per_token": 2.275e-07, - "output_cost_per_token": 9.1e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 2.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 16384, @@ -66437,8 +66668,8 @@ "supports_prompt_caching": true }, "openrouter/meta-llama/llama-4-maverick": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6.96e-07, + "input_cost_per_token": 1.875e-07, + "output_cost_per_token": 6.525e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 115200, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 7feef3be8ea..231169b4c9f 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -7566,6 +7566,70 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-sol-2026-07-09": { + "cache_creation_input_token_cost": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_flex": 5e-06, + "cache_creation_input_token_cost_priority": 1e-05, + "cache_creation_input_token_cost_above_272k_tokens_priority": 2e-05, + "cache_creation_input_token_cost_flex": 2.5e-06, + "cache_read_input_token_cost": 4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07, + "cache_read_input_token_cost_priority": 8e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06, + "cache_read_input_token_cost_flex": 2e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 4e-06, + "input_cost_per_token_above_272k_tokens": 8e-06, + "input_cost_per_token_above_272k_tokens_flex": 4e-06, + "input_cost_per_token_priority": 8e-06, + "input_cost_per_token_above_272k_tokens_priority": 1.6e-05, + "input_cost_per_token_flex": 2e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 2e-05, + "output_cost_per_token_above_272k_tokens": 3e-05, + "output_cost_per_token_above_272k_tokens_flex": 1.5e-05, + "output_cost_per_token_priority": 4e-05, + "output_cost_per_token_above_272k_tokens_priority": 6e-05, + "output_cost_per_token_flex": 1e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure/gpt-5.6-terra": { "cache_creation_input_token_cost": 2.5e-06, "cache_creation_input_token_cost_above_272k_tokens": 5e-06, @@ -7630,6 +7694,70 @@ "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false }, + "azure/gpt-5.6-terra-2026-07-09": { + "cache_creation_input_token_cost": 2.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-06, + "cache_creation_input_token_cost_priority": 5e-06, + "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-05, + "cache_creation_input_token_cost_flex": 1.25e-06, + "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost_above_272k_tokens": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07, + "cache_read_input_token_cost_priority": 4e-07, + "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07, + "cache_read_input_token_cost_flex": 1e-07, + "deprecation_date": "2028-01-11", + "input_cost_per_token": 2e-06, + "input_cost_per_token_above_272k_tokens": 4e-06, + "input_cost_per_token_above_272k_tokens_flex": 2e-06, + "input_cost_per_token_priority": 4e-06, + "input_cost_per_token_above_272k_tokens_priority": 8e-06, + "input_cost_per_token_flex": 1e-06, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 1.2e-05, + "output_cost_per_token_above_272k_tokens": 1.8e-05, + "output_cost_per_token_above_272k_tokens_flex": 9e-06, + "output_cost_per_token_priority": 2.4e-05, + "output_cost_per_token_above_272k_tokens_priority": 3.6e-05, + "output_cost_per_token_flex": 6e-06, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/batch", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_native_streaming": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_none_reasoning_effort": true, + "supports_xhigh_reasoning_effort": true, + "supports_minimal_reasoning_effort": false + }, "azure/gpt-5.6-luna": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, @@ -7798,6 +7926,54 @@ "supports_web_search": true, "supports_xhigh_reasoning_effort": true }, + "azure/gpt-6-astra-2026-09-03": { + "cache_creation_input_token_cost": 1.25e-05, + "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05, + "cache_read_input_token_cost": 1e-06, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, + "input_cost_per_token": 1e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "litellm_provider": "azure", + "max_input_tokens": 922000, + "max_output_tokens": 128000, + "max_tokens": 128000, + "mode": "chat", + "output_cost_per_token": 5e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.01, + "search_context_size_low": 0.01, + "search_context_size_medium": 0.01 + }, + "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses" + ], + "supported_modalities": [ + "text", + "image" + ], + "supported_output_modalities": [ + "text" + ], + "supports_computer_use": true, + "supports_function_calling": true, + "supports_max_reasoning_effort": false, + "supports_minimal_reasoning_effort": false, + "supports_native_streaming": true, + "supports_none_reasoning_effort": true, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "azure/gpt-chat-latest": { "cache_read_input_token_cost": 5e-07, "deprecation_date": "2026-12-02", @@ -14186,7 +14362,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -14221,7 +14397,7 @@ "cache_creation_input_token_cost_above_200k_tokens": 7.5e-06, "cache_read_input_token_cost_above_200k_tokens": 6e-07, "litellm_provider": "anthropic", - "max_input_tokens": 200000, + "max_input_tokens": 1000000, "max_output_tokens": 64000, "max_tokens": 64000, "mode": "chat", @@ -14242,7 +14418,8 @@ "supports_tool_choice": true, "supports_vision": true, "supports_web_search": true, - "prompt_cache_min_tokens": 1024 + "prompt_cache_min_tokens": 1024, + "source": "https://docs.anthropic.com/en/docs/about-claude/pricing" }, "claude-sonnet-5": { "deprecation_date": "2027-06-30", @@ -32459,7 +32636,7 @@ "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", @@ -32498,7 +32675,7 @@ "input_cost_per_token": 4e-06, "input_cost_per_token_above_272k_tokens": 8e-06, "litellm_provider": "openai", - "max_input_tokens": 1050000, + "max_input_tokens": 922000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "responses", @@ -36833,6 +37010,57 @@ "supports_response_schema": true, "supports_tool_choice": true }, + "mistral/zai-glm-5-3": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-5": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, + "mistral/zai-glm-latest": { + "cache_read_input_token_cost": 1.4e-07, + "input_cost_per_token": 1.4e-06, + "litellm_provider": "mistral", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.4e-06, + "source": "https://docs.mistral.ai/models/zai-glm-5-3", + "supports_assistant_prefill": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true + }, "mistral/glm-5-2": { "cache_read_input_token_cost": 1.4e-07, "input_cost_per_token": 1.4e-06, @@ -40578,15 +40806,16 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-chat": { - "input_cost_per_token": 3.2e-07, + "input_cost_per_token": 2.574e-07, "litellm_provider": "openrouter", "max_input_tokens": 65536, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 8.9e-07, + "output_cost_per_token": 1.0287e-06, "supports_prompt_caching": true, - "supports_tool_choice": true + "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/deepseek/deepseek-chat-v3-0324": { "input_cost_per_token": 2.5e-07, @@ -40679,21 +40908,21 @@ "supports_tool_choice": true }, "openrouter/deepseek/deepseek-v4-pro": { - "input_cost_per_token": 8.59908e-07, + "input_cost_per_token": 1.6e-06, "input_cost_per_token_cache_hit": 4.4e-08, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 384000, "max_tokens": 384000, "mode": "chat", - "output_cost_per_token": 1.719816e-06, + "output_cost_per_token": 3.2e-06, "source": "https://openrouter.ai/deepseek/deepseek-v4-pro", "supports_function_calling": true, "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "cache_read_input_token_cost": 7.1659e-08 + "cache_read_input_token_cost": 1.35e-07 }, "openrouter/deepseek/deepseek-v4.1-flash": { "input_cost_per_token": 1.5e-07, @@ -40988,12 +41217,13 @@ "supports_vision": true }, "openrouter/gryphe/mythomax-l2-13b": { - "input_cost_per_token": 6e-08, + "input_cost_per_token": 8e-08, "litellm_provider": "openrouter", "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 6e-08, - "supports_tool_choice": true + "output_cost_per_token": 1.1e-07, + "supports_tool_choice": true, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/mancer/weaver": { "input_cost_per_token": 4e-07, @@ -41129,14 +41359,15 @@ "max_output_tokens": 131072 }, "openrouter/mistralai/mistral-small-3.2-24b-instruct": { - "input_cost_per_token": 7.5e-08, + "input_cost_per_token": 9.375e-08, "litellm_provider": "openrouter", "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 2e-07, + "output_cost_per_token": 2.5e-07, "supports_tool_choice": true, "max_input_tokens": 128000, - "max_output_tokens": 128000 + "max_output_tokens": 128000, + "source": "https://openrouter.ai/api/v1/models" }, "openrouter/mistralai/mixtral-8x22b-instruct": { "input_cost_per_token": 2e-06, @@ -41657,13 +41888,13 @@ "supports_tool_choice": true }, "openrouter/qwen/qwen3-235b-a22b-2507": { - "input_cost_per_token": 2.2e-07, + "input_cost_per_token": 8.75e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 262144, "max_tokens": 262144, "mode": "chat", - "output_cost_per_token": 8.8e-07, + "output_cost_per_token": 3.5e-07, "source": "https://openrouter.ai/qwen/qwen3-235b-a22b-2507", "supports_function_calling": true, "supports_tool_choice": true @@ -41696,13 +41927,13 @@ "supports_vision": true }, "openrouter/qwen/qwen3.5-35b-a3b": { - "input_cost_per_token": 3.125e-07, + "input_cost_per_token": 1.625e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 65536, "max_tokens": 65536, "mode": "chat", - "output_cost_per_token": 1.25e-06, + "output_cost_per_token": 1.3e-06, "source": "https://openrouter.ai/qwen/qwen3.5-35b-a3b", "supports_function_calling": true, "supports_reasoning": true, @@ -44718,7 +44949,7 @@ "deprecation_date": "2026-06-04", "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", - "max_input_tokens": 256000, + "max_input_tokens": 262144, "mode": "chat", "output_cost_per_token": 2e-06, "source": "https://api.together.ai/v1/models", @@ -44788,7 +45019,7 @@ "supports_parallel_function_calling": true, "supports_reasoning": true, "supports_tool_choice": true, - "max_input_tokens": 128000, + "max_input_tokens": 131072, "max_output_tokens": 16384 }, "together_ai/meta-llama/Llama-3.2-3B-Instruct-Turbo": { @@ -44971,7 +45202,7 @@ "deprecation_date": "2026-04-02", "input_cost_per_token": 2e-07, "litellm_provider": "together_ai", - "max_input_tokens": 128000, + "max_input_tokens": 131072, "mode": "chat", "output_cost_per_token": 1.1e-06, "source": "https://api.together.ai/v1/models", @@ -64723,9 +64954,9 @@ "supports_prompt_caching": true }, "openrouter/z-ai/glm-5.3-flash": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 5e-07, - "cache_read_input_token_cost": 3e-08, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, + "cache_read_input_token_cost": 1.8e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 131072, @@ -64775,9 +65006,9 @@ "supports_prompt_caching": true }, "openrouter/qwen/qwen3.8-27b": { - "input_cost_per_token": 4.2e-07, - "output_cost_per_token": 3e-06, - "cache_read_input_token_cost": 8.5e-08, + "input_cost_per_token": 2.14e-07, + "output_cost_per_token": 2.55e-06, + "cache_read_input_token_cost": 1.5e-07, "litellm_provider": "openrouter", "max_input_tokens": 1000000, "max_output_tokens": 131072, @@ -64860,9 +65091,9 @@ "supports_prompt_caching": true }, "openrouter/deepseek/deepseek-v4-flash-0731": { - "input_cost_per_token": 6.5e-08, - "output_cost_per_token": 1.8e-07, - "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 6e-08, + "output_cost_per_token": 1.2e-07, + "cache_read_input_token_cost": 1.2e-08, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943718, @@ -64930,9 +65161,9 @@ "supports_vision": false }, "openrouter/moonshotai/kimi-k3": { - "input_cost_per_token": 2.1e-06, - "output_cost_per_token": 1.053e-05, - "cache_read_input_token_cost": 2.35e-07, + "input_cost_per_token": 3e-06, + "output_cost_per_token": 1.5e-05, + "cache_read_input_token_cost": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 943718, @@ -65029,9 +65260,9 @@ "supports_prompt_caching": true }, "openrouter/z-ai/glm-5.2": { - "input_cost_per_token": 6e-07, - "output_cost_per_token": 2e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 1.4e-06, + "output_cost_per_token": 4.4e-06, + "cache_read_input_token_cost": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 131072, @@ -65062,9 +65293,9 @@ "supports_vision": false }, "openrouter/moonshotai/kimi-k2.7-code": { - "input_cost_per_token": 7.1e-07, - "output_cost_per_token": 3.5e-06, - "cache_read_input_token_cost": 1.5e-07, + "input_cost_per_token": 7.062e-07, + "output_cost_per_token": 3.21e-06, + "cache_read_input_token_cost": 1.8e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 235929, @@ -65366,8 +65597,8 @@ "supports_prompt_caching": true }, "openrouter/google/gemma-4-26b-a4b-it": { - "input_cost_per_token": 4.2e-08, - "output_cost_per_token": 2.2e-07, + "input_cost_per_token": 9e-08, + "output_cost_per_token": 3e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 16384, @@ -65914,8 +66145,8 @@ "supports_vision": true }, "openrouter/qwen/qwen3-vl-30b-a3b-instruct": { - "input_cost_per_token": 1.5e-07, - "output_cost_per_token": 6e-07, + "input_cost_per_token": 1.3e-07, + "output_cost_per_token": 5.2e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 16384, @@ -66175,8 +66406,8 @@ "supports_vision": false }, "openrouter/qwen/qwen3-30b-a3b-instruct-2507": { - "input_cost_per_token": 9e-08, - "output_cost_per_token": 3e-07, + "input_cost_per_token": 4.815e-08, + "output_cost_per_token": 1.9305e-07, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 32000, @@ -66235,7 +66466,7 @@ "supports_vision": false }, "openrouter/minimax/minimax-m1": { - "input_cost_per_token": 5.5e-07, + "input_cost_per_token": 4e-07, "output_cost_per_token": 2.2e-06, "litellm_provider": "openrouter", "max_input_tokens": 1000000, @@ -66374,8 +66605,8 @@ "supports_vision": false }, "openrouter/qwen/qwen3-14b": { - "input_cost_per_token": 2.275e-07, - "output_cost_per_token": 9.1e-07, + "input_cost_per_token": 1.2e-07, + "output_cost_per_token": 2.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 131072, "max_output_tokens": 16384, @@ -66437,8 +66668,8 @@ "supports_prompt_caching": true }, "openrouter/meta-llama/llama-4-maverick": { - "input_cost_per_token": 2e-07, - "output_cost_per_token": 6.96e-07, + "input_cost_per_token": 1.875e-07, + "output_cost_per_token": 6.525e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 115200, From 8caf2cb61f33dcb55d5b48d3cb698618bba1526d Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 19:17:45 +0000 Subject: [PATCH 13/16] fix(models): flag prompt caching on Vertex and Azure AI Grok rows Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 8 +++ model_prices_and_context_window.json | 8 +++ ...tex_ai_xai_grok_prompt_caching_metadata.py | 58 +++++++++++++++++++ 3 files changed, 74 insertions(+) create mode 100644 tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 231169b4c9f..dbd42728888 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -11833,6 +11833,7 @@ "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -11851,6 +11852,7 @@ "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -50027,6 +50029,7 @@ "output_cost_per_token": 5e-07, "source": "https://docs.x.ai/developers/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -50043,6 +50046,7 @@ "output_cost_per_token": 5e-07, "source": "https://docs.x.ai/developers/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -50063,6 +50067,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -50082,6 +50087,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -50102,6 +50108,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -50121,6 +50128,7 @@ "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 231169b4c9f..dbd42728888 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -11833,6 +11833,7 @@ "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -11851,6 +11852,7 @@ "output_cost_per_token": 2.5e-06, "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -50027,6 +50029,7 @@ "output_cost_per_token": 5e-07, "source": "https://docs.x.ai/developers/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -50043,6 +50046,7 @@ "output_cost_per_token": 5e-07, "source": "https://docs.x.ai/developers/models", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -50063,6 +50067,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_vision": true, @@ -50082,6 +50087,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -50102,6 +50108,7 @@ "output_cost_per_token_above_200k_tokens": 5e-06, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, @@ -50121,6 +50128,7 @@ "output_cost_per_token_above_200k_tokens": 1.2e-05, "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing", "supports_function_calling": true, + "supports_prompt_caching": true, "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, diff --git a/tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py b/tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py new file mode 100644 index 00000000000..b8b3897f004 --- /dev/null +++ b/tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py @@ -0,0 +1,58 @@ +from pathlib import Path +from typing import Final + +import pytest +from pydantic import TypeAdapter + +from litellm import get_model_info +from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider +from litellm.utils import supports_prompt_caching + +REPO_ROOT: Final = Path(__file__).parents[2] +MODEL: Final = "vertex_ai/xai/grok-4.6" +GROK_KEY_PREFIXES: Final = ("vertex_ai/xai/grok-", "azure_ai/grok-", "xai/grok-") +COST_MAP_ADAPTER: Final = TypeAdapter(dict[str, dict[str, object]]) +MAIN_COST_MAP: Final = REPO_ROOT / "model_prices_and_context_window.json" +BACKUP_COST_MAP: Final = REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json" + + +def _cost_map(path: Path) -> dict[str, dict[str, object]]: + return COST_MAP_ADAPTER.validate_json(path.read_bytes()) + + +def test_grok_entries_with_cache_read_price_advertise_prompt_caching() -> None: + cost_map = _cost_map(MAIN_COST_MAP) + cached_grok_entries = tuple( + (key, entry) + for key, entry in cost_map.items() + if key.startswith(GROK_KEY_PREFIXES) and entry.get("cache_read_input_token_cost") + ) + assert cached_grok_entries, "expected at least one grok entry with a cache read price" + + missing_flag = tuple(key for key, entry in cached_grok_entries if entry.get("supports_prompt_caching") is not True) + assert missing_flag == (), ( + f"grok entries with cache_read_input_token_cost missing supports_prompt_caching: {missing_flag}" + ) + + +@pytest.mark.usefixtures("local_model_cost_map") +def test_vertex_ai_grok_4_6_supports_prompt_caching_via_get_model_info() -> None: + routed_model, provider, _, _ = get_llm_provider(model=MODEL) + assert (routed_model, provider) == ("xai/grok-4.6", "vertex_ai") + + info = get_model_info(model=routed_model, custom_llm_provider=provider) + assert info["litellm_provider"] == "vertex_ai" + assert info.get("supports_prompt_caching") is True + + assert supports_prompt_caching(model=MODEL) is True + + +def test_vertex_ai_grok_entries_source_and_backup_match() -> None: + main_map = _cost_map(MAIN_COST_MAP) + backup_map = _cost_map(BACKUP_COST_MAP) + + vertex_grok_keys = tuple(key for key in main_map if key.startswith("vertex_ai/xai/grok-")) + assert vertex_grok_keys, "expected at least one vertex_ai/xai/grok- entry" + + mismatched = tuple(key for key in vertex_grok_keys if backup_map.get(key) != main_map[key]) + assert mismatched == (), f"vertex grok entries differ between source and backup: {mismatched}" From 93eefc5922493d59b8ed08072ff072bc0acf32e2 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 19:20:20 +0000 Subject: [PATCH 14/16] fix(models): dedupe Fireworks deprecation keys and sync Azure dated snapshot service tiers Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 33 +++++++++++-------- model_prices_and_context_window.json | 33 +++++++++++-------- 2 files changed, 40 insertions(+), 26 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index dbd42728888..2575b227bfc 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -7825,17 +7825,23 @@ "azure/gpt-5.6-luna-2026-07-09": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_priority": 4e-07, "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_flex": 1e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7843,8 +7849,10 @@ "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_priority": 2.4e-06, "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -8794,12 +8802,15 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -8807,7 +8818,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8894,7 +8905,7 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -8991,7 +9002,7 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -23348,8 +23359,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "deprecation_date": "2026-08-27" + "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, @@ -23737,8 +23747,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "deprecation_date": "2026-08-27" + "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/minimax-m3": { "cache_read_input_token_cost": 6e-08, @@ -23845,8 +23854,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "deprecation_date": "2026-08-27" + "supports_vision": false }, "fireworks_ai/glm-4p7": { "cache_read_input_token_cost": 3e-07, @@ -24065,8 +24073,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "deprecation_date": "2026-08-27" + "supports_vision": false }, "fireworks_ai/minimax-m3": { "cache_read_input_token_cost": 6e-08, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index dbd42728888..2575b227bfc 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -7825,17 +7825,23 @@ "azure/gpt-5.6-luna-2026-07-09": { "cache_creation_input_token_cost": 2.5e-07, "cache_creation_input_token_cost_above_272k_tokens": 5e-07, + "cache_creation_input_token_cost_above_272k_tokens_flex": 2.5e-07, "cache_creation_input_token_cost_priority": 5e-07, "cache_creation_input_token_cost_above_272k_tokens_priority": 1e-06, + "cache_creation_input_token_cost_flex": 1.25e-07, "cache_read_input_token_cost": 2e-08, "cache_read_input_token_cost_above_272k_tokens": 4e-08, + "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08, "cache_read_input_token_cost_priority": 4e-08, "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08, + "cache_read_input_token_cost_flex": 1e-08, "deprecation_date": "2028-01-11", "input_cost_per_token": 2e-07, "input_cost_per_token_above_272k_tokens": 4e-07, + "input_cost_per_token_above_272k_tokens_flex": 2e-07, "input_cost_per_token_priority": 4e-07, "input_cost_per_token_above_272k_tokens_priority": 8e-07, + "input_cost_per_token_flex": 1e-07, "litellm_provider": "azure", "max_input_tokens": 922000, "max_output_tokens": 128000, @@ -7843,8 +7849,10 @@ "mode": "chat", "output_cost_per_token": 1.2e-06, "output_cost_per_token_above_272k_tokens": 1.8e-06, + "output_cost_per_token_above_272k_tokens_flex": 9e-07, "output_cost_per_token_priority": 2.4e-06, "output_cost_per_token_above_272k_tokens_priority": 3.6e-06, + "output_cost_per_token_flex": 6e-07, "search_context_cost_per_query": { "search_context_size_high": 0.01, "search_context_size_low": 0.01, @@ -8794,12 +8802,15 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5e-07, "cache_read_input_token_cost_above_272k_tokens": 1e-06, - "cache_read_input_token_cost_priority": 1e-06, + "cache_read_input_token_cost_priority": 1.25e-06, "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, + "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, - "input_cost_per_token_priority": 1e-05, + "input_cost_per_token_above_272k_tokens_flex": 5e-06, + "input_cost_per_token_priority": 1.25e-05, "input_cost_per_token_above_272k_tokens_priority": 2e-05, + "input_cost_per_token_flex": 2.5e-06, "litellm_provider": "azure", "max_input_tokens": 1050000, "max_output_tokens": 128000, @@ -8807,7 +8818,7 @@ "mode": "chat", "output_cost_per_token": 3e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, - "output_cost_per_token_priority": 6e-05, + "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, "search_context_cost_per_query": { "search_context_size_high": 0.01, @@ -8894,7 +8905,7 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -8991,7 +9002,7 @@ "deprecation_date": "2027-10-26", "cache_read_input_token_cost": 5.5e-07, "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "cache_read_input_token_cost_priority": 1.38e-06, + "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, @@ -23348,8 +23359,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "deprecation_date": "2026-08-27" + "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": { "cache_read_input_token_cost": 4.4e-08, @@ -23737,8 +23747,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "deprecation_date": "2026-08-27" + "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/minimax-m3": { "cache_read_input_token_cost": 6e-08, @@ -23845,8 +23854,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "deprecation_date": "2026-08-27" + "supports_vision": false }, "fireworks_ai/glm-4p7": { "cache_read_input_token_cost": 3e-07, @@ -24065,8 +24073,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": false, - "deprecation_date": "2026-08-27" + "supports_vision": false }, "fireworks_ai/minimax-m3": { "cache_read_input_token_cost": 6e-08, From ba03f60f7143f5d5b78228b63c1a0fe8043642f8 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 19:50:28 +0000 Subject: [PATCH 15/16] fix(models): add batch and flex tier prices on Azure dated and Gemini latest alias rows Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../model_prices_and_context_window_backup.json | 16 ++++++++++++++-- model_prices_and_context_window.json | 16 ++++++++++++++-- 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 2575b227bfc..0f3535d9b18 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -8806,6 +8806,7 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_priority": 1.25e-05, @@ -8817,6 +8818,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, + "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, @@ -8907,9 +8909,11 @@ "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", @@ -9004,9 +9008,11 @@ "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", @@ -56989,7 +56995,10 @@ "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-pro-latest": { "cache_read_input_token_cost": 2e-07, @@ -57048,7 +57057,10 @@ "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-exp-1206": { "cache_read_input_token_cost": 3e-08, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 2575b227bfc..0f3535d9b18 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -8806,6 +8806,7 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_priority": 1.25e-05, @@ -8817,6 +8818,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, + "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, @@ -8907,9 +8909,11 @@ "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", @@ -9004,9 +9008,11 @@ "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", @@ -56989,7 +56995,10 @@ "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-pro-latest": { "cache_read_input_token_cost": 2e-07, @@ -57048,7 +57057,10 @@ "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-exp-1206": { "cache_read_input_token_cost": 3e-08, From a229f99ac8f924b8d3499186a97bc8b5fb3cff29 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 19:59:07 +0000 Subject: [PATCH 16/16] test(models): drive Grok prompt caching coverage through litellm APIs Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...tex_ai_xai_grok_prompt_caching_metadata.py | 38 +++++-------------- 1 file changed, 9 insertions(+), 29 deletions(-) diff --git a/tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py b/tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py index b8b3897f004..72e98711f0c 100644 --- a/tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py +++ b/tests/test_litellm/test_vertex_ai_xai_grok_prompt_caching_metadata.py @@ -1,37 +1,28 @@ -from pathlib import Path from typing import Final import pytest -from pydantic import TypeAdapter +import litellm from litellm import get_model_info from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider from litellm.utils import supports_prompt_caching -REPO_ROOT: Final = Path(__file__).parents[2] MODEL: Final = "vertex_ai/xai/grok-4.6" GROK_KEY_PREFIXES: Final = ("vertex_ai/xai/grok-", "azure_ai/grok-", "xai/grok-") -COST_MAP_ADAPTER: Final = TypeAdapter(dict[str, dict[str, object]]) -MAIN_COST_MAP: Final = REPO_ROOT / "model_prices_and_context_window.json" -BACKUP_COST_MAP: Final = REPO_ROOT / "litellm" / "model_prices_and_context_window_backup.json" -def _cost_map(path: Path) -> dict[str, dict[str, object]]: - return COST_MAP_ADAPTER.validate_json(path.read_bytes()) - - -def test_grok_entries_with_cache_read_price_advertise_prompt_caching() -> None: - cost_map = _cost_map(MAIN_COST_MAP) - cached_grok_entries = tuple( - (key, entry) - for key, entry in cost_map.items() +@pytest.mark.usefixtures("local_model_cost_map") +def test_grok_models_with_cache_read_price_advertise_prompt_caching() -> None: + cached_grok_models = tuple( + key + for key, entry in litellm.model_cost.items() if key.startswith(GROK_KEY_PREFIXES) and entry.get("cache_read_input_token_cost") ) - assert cached_grok_entries, "expected at least one grok entry with a cache read price" + assert cached_grok_models, "expected at least one grok model with a cache read price" - missing_flag = tuple(key for key, entry in cached_grok_entries if entry.get("supports_prompt_caching") is not True) + missing_flag = tuple(key for key in cached_grok_models if supports_prompt_caching(model=key) is not True) assert missing_flag == (), ( - f"grok entries with cache_read_input_token_cost missing supports_prompt_caching: {missing_flag}" + f"grok models with cache_read_input_token_cost fail supports_prompt_caching: {missing_flag}" ) @@ -45,14 +36,3 @@ def test_vertex_ai_grok_4_6_supports_prompt_caching_via_get_model_info() -> None assert info.get("supports_prompt_caching") is True assert supports_prompt_caching(model=MODEL) is True - - -def test_vertex_ai_grok_entries_source_and_backup_match() -> None: - main_map = _cost_map(MAIN_COST_MAP) - backup_map = _cost_map(BACKUP_COST_MAP) - - vertex_grok_keys = tuple(key for key in main_map if key.startswith("vertex_ai/xai/grok-")) - assert vertex_grok_keys, "expected at least one vertex_ai/xai/grok- entry" - - mismatched = tuple(key for key in vertex_grok_keys if backup_map.get(key) != main_map[key]) - assert mismatched == (), f"vertex grok entries differ between source and backup: {mismatched}"