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] 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,