diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index c565b6ecc4b..96cdbcffd90 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -7605,7 +7605,7 @@ "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", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7733,7 +7733,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7887,7 +7887,7 @@ "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" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, @@ -7956,7 +7956,7 @@ "search_context_size_low": 0.01, "search_context_size_medium": 0.01 }, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8856,7 +8856,7 @@ "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" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -8955,7 +8955,7 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -9054,7 +9054,7 @@ "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" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -10987,14 +10987,14 @@ "supports_vision": true }, "azure_ai/FW-Kimi-K3": { - "cache_read_input_token_cost": 3.3e-07, - "input_cost_per_token": 3.3e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.65e-05, + "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ "low", "high", @@ -23788,7 +23788,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { "input_cost_per_token": 1.2e-06, @@ -24114,7 +24114,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "fireworks_ai/qwen3p7-plus": { "cache_read_input_token_cost": 8e-08, @@ -45245,7 +45245,7 @@ "supports_tool_choice": true }, "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-15", + "deprecation_date": "2026-09-14", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -45482,6 +45482,7 @@ }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2026-09-29", "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -45503,7 +45504,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://api.together.xyz/v1/models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -45528,6 +45529,7 @@ }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 1.3e-07, + "deprecation_date": "2026-09-29", "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -45552,7 +45554,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-15", + "deprecation_date": "2026-09-14", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -45567,7 +45569,7 @@ "supports_vision": true }, "together_ai/intfloat/multilingual-e5-large-instruct": { - "deprecation_date": "2026-09-15", + "deprecation_date": "2026-09-14", "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "max_input_tokens": 514, @@ -45680,7 +45682,7 @@ "supports_tool_choice": true }, "together_ai/thinkingmachines/Inkling-Small": { - "deprecation_date": "2026-09-15", + "deprecation_date": "2026-09-14", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", @@ -50573,7 +50575,7 @@ "wandb/openai/gpt-oss-120b": { "supports_reasoning": true, "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, "output_cost_per_token": 1.7e-07, @@ -50584,7 +50586,7 @@ "wandb/openai/gpt-oss-20b": { "supports_reasoning": true, "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, "output_cost_per_token": 1.3e-07, @@ -50593,6 +50595,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/zai-org/GLM-4.5": { + "deprecation_date": "2026-03-04", "supports_reasoning": true, "max_tokens": 131072, "max_input_tokens": 131072, @@ -50603,6 +50606,7 @@ "mode": "chat" }, "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "deprecation_date": "2026-08-04", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -50612,6 +50616,7 @@ "mode": "chat" }, "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "deprecation_date": "2026-08-25", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -50622,6 +50627,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "deprecation_date": "2026-08-04", "supports_reasoning": true, "max_tokens": 262144, "max_input_tokens": 262144, @@ -50632,6 +50638,7 @@ "mode": "chat" }, "wandb/moonshotai/Kimi-K2-Instruct": { + "deprecation_date": "2026-03-04", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -50656,6 +50663,7 @@ "supports_vision": true }, "wandb/MiniMaxAI/MiniMax-M2.5": { + "deprecation_date": "2026-08-25", "max_tokens": 197000, "max_input_tokens": 197000, "max_output_tokens": 197000, @@ -50670,7 +50678,7 @@ }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { "max_tokens": 128000, - "max_input_tokens": 128000, + "max_input_tokens": 131000, "max_output_tokens": 128000, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 2.2e-07, @@ -50690,6 +50698,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-R1-0528": { + "deprecation_date": "2026-03-04", "supports_reasoning": true, "max_tokens": 161000, "max_input_tokens": 161000, @@ -50700,6 +50709,7 @@ "mode": "chat" }, "wandb/deepseek-ai/DeepSeek-V3-0324": { + "deprecation_date": "2026-03-04", "max_tokens": 161000, "max_input_tokens": 161000, "max_output_tokens": 161000, @@ -50719,6 +50729,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2026-04-21", "max_tokens": 64000, "max_input_tokens": 64000, "max_output_tokens": 64000, @@ -50728,6 +50739,7 @@ "mode": "chat" }, "wandb/microsoft/Phi-4-mini-instruct": { + "deprecation_date": "2026-08-04", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -56692,7 +56704,8 @@ "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, - "gemini_audio_only_live": true + "gemini_audio_only_live": true, + "supports_response_schema": false }, "gemini-3.8-live-extended-thinking": { "input_cost_per_audio_token": 3e-06, @@ -56726,7 +56739,8 @@ "supports_vision": true, "supports_web_search": true, "gemini_audio_only_live": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": false }, "gemini/gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, @@ -60970,10 +60984,11 @@ "wandb/deepseek-ai/DeepSeek-V4-Flash": { "supports_reasoning": true, "max_tokens": 1048576, - "max_input_tokens": 1048576, + "max_input_tokens": 1049000, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 7e-08, + "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -60983,7 +60998,7 @@ "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 7e-08, @@ -60996,10 +61011,11 @@ "wandb/deepseek-ai/DeepSeek-V4-Pro": { "supports_reasoning": true, "max_tokens": 1048576, - "max_input_tokens": 1048576, + "max_input_tokens": 1049000, "input_cost_per_token": 1.15e-06, "output_cost_per_token": 2.55e-06, "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -61009,7 +61025,7 @@ "wandb/google/gemma-4-31B-it": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3.4e-07, "litellm_provider": "wandb", @@ -61018,8 +61034,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/ibm-granite/granite-4.1-8b": { + "deprecation_date": "2026-10-05", "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, "litellm_provider": "wandb", @@ -61028,8 +61045,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { + "deprecation_date": "2026-10-05", "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, "litellm_provider": "wandb", @@ -61038,8 +61056,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/meta-llama/Llama-3.1-70B-Instruct": { + "deprecation_date": "2026-10-05", "max_tokens": 128000, - "max_input_tokens": 128000, + "max_input_tokens": 131000, "input_cost_per_token": 8e-07, "output_cost_per_token": 8e-07, "litellm_provider": "wandb", @@ -61050,7 +61069,7 @@ "wandb/MiniMaxAI/MiniMax-M3": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 2.3e-07, "output_cost_per_token": 9.6e-07, "cache_read_input_token_cost": 5e-08, @@ -61063,7 +61082,7 @@ "wandb/moonshotai/Kimi-K2.7-Code": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 7.1e-07, "output_cost_per_token": 3.5e-06, "cache_read_input_token_cost": 1.5e-07, @@ -61076,7 +61095,7 @@ "wandb/moonshotai/Kimi-K2.6": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 6.5e-07, "output_cost_per_token": 3.41e-06, "cache_read_input_token_cost": 1.5e-07, @@ -61089,10 +61108,10 @@ "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2.5e-07, - "cache_read_input_token_cost": 5e-08, + "max_input_tokens": 262000, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 4e-08, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -61102,10 +61121,10 @@ "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 2.75e-06, - "cache_read_input_token_cost": 1.5e-07, + "max_input_tokens": 262000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.15e-06, + "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -61113,8 +61132,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/OpenPipe/Qwen3-14B-Instruct": { + "deprecation_date": "2026-10-05", "max_tokens": 32768, - "max_input_tokens": 32768, + "max_input_tokens": 32800, "input_cost_per_token": 5e-08, "output_cost_per_token": 2.2e-07, "litellm_provider": "wandb", @@ -61125,7 +61145,7 @@ "wandb/Qwen/Qwen3.8-27B": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 1.5e-07, @@ -61138,7 +61158,7 @@ "wandb/Qwen/Qwen3.6-35B-A3B": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, "litellm_provider": "wandb", @@ -61149,10 +61169,11 @@ "wandb/Qwen/Qwen3.6-27B": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 6e-07, "output_cost_per_token": 3.6e-06, "cache_read_input_token_cost": 1.2e-07, + "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -61160,9 +61181,10 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3.5-35B-A3B": { + "deprecation_date": "2026-10-05", "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, "litellm_provider": "wandb", @@ -61171,8 +61193,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { + "deprecation_date": "2026-10-05", "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "wandb", @@ -61187,6 +61210,7 @@ "input_cost_per_token": 1.31e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 4.4e-08, + "max_input_tokens": 1049000, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/" }, @@ -61197,13 +61221,14 @@ "input_cost_per_token": 1e-07, "output_cost_per_token": 1.5e-07, "cache_read_input_token_cost": 5e-08, + "max_input_tokens": 131000, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/zai-org/GLM-5.2": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 1049000, "input_cost_per_token": 7.6e-07, "output_cost_per_token": 2.42e-06, "cache_read_input_token_cost": 1.4e-07, @@ -62866,7 +62891,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -69158,5 +69183,19 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true + }, + "wandb/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://wandb.ai/site/pricing/tokens/", + "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 c565b6ecc4b..96cdbcffd90 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -7605,7 +7605,7 @@ "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", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7733,7 +7733,7 @@ "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", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -7887,7 +7887,7 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-6-astra": { "cache_creation_input_token_cost": 1.25e-05, @@ -7956,7 +7956,7 @@ "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", + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'", "supported_endpoints": [ "/v1/chat/completions", "/v1/responses" @@ -8856,7 +8856,7 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/us/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -8955,7 +8955,7 @@ "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" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/eu/gpt-5.5-2026-04-23": { "cache_read_input_token_cost": 5.5e-07, @@ -9054,7 +9054,7 @@ "supports_none_reasoning_effort": true, "supports_xhigh_reasoning_effort": true, "supports_minimal_reasoning_effort": false, - "source": "https://learn.microsoft.com/en-us/azure/ai-foundry/openai/concepts/models" + "source": "https://prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'" }, "azure/gpt-5.5-pro": { "cache_read_input_token_cost": 3e-06, @@ -10987,14 +10987,14 @@ "supports_vision": true }, "azure_ai/FW-Kimi-K3": { - "cache_read_input_token_cost": 3.3e-07, - "input_cost_per_token": 3.3e-06, + "cache_read_input_token_cost": 3e-07, + "input_cost_per_token": 3e-06, "litellm_provider": "azure_ai", "max_input_tokens": 1048576, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 1.65e-05, + "output_cost_per_token": 1.5e-05, "reasoning_effort_levels": [ "low", "high", @@ -23788,7 +23788,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "fireworks_ai/accounts/fireworks/models/mixtral-8x22b-instruct-hf": { "input_cost_per_token": 1.2e-06, @@ -24114,7 +24114,7 @@ "supports_reasoning": true, "supports_response_schema": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": false }, "fireworks_ai/qwen3p7-plus": { "cache_read_input_token_cost": 8e-08, @@ -45245,7 +45245,7 @@ "supports_tool_choice": true }, "together_ai/openai/gpt-oss-20b": { - "deprecation_date": "2026-09-15", + "deprecation_date": "2026-09-14", "input_cost_per_token": 5e-08, "litellm_provider": "together_ai", "max_input_tokens": 131072, @@ -45482,6 +45482,7 @@ }, "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": { "cache_read_input_token_cost": 3e-08, + "deprecation_date": "2026-09-29", "input_cost_per_token": 1.4e-07, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -45503,7 +45504,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 1.2e-06, - "source": "https://api.together.xyz/v1/models", + "source": "https://api.together.ai/v1/models", "supports_function_calling": true, "supports_prompt_caching": true, "supports_response_schema": true, @@ -45528,6 +45529,7 @@ }, "together_ai/deepseek-ai/DeepSeek-V4-Pro-0813": { "cache_read_input_token_cost": 1.3e-07, + "deprecation_date": "2026-09-29", "input_cost_per_token": 1.32e-06, "litellm_provider": "together_ai", "max_input_tokens": 1048576, @@ -45552,7 +45554,7 @@ "source": "https://docs.together.ai/docs/serverless-models" }, "together_ai/google/gemma-4-31B-it": { - "deprecation_date": "2026-09-15", + "deprecation_date": "2026-09-14", "input_cost_per_token": 3.9e-07, "litellm_provider": "together_ai", "max_input_tokens": 262144, @@ -45567,7 +45569,7 @@ "supports_vision": true }, "together_ai/intfloat/multilingual-e5-large-instruct": { - "deprecation_date": "2026-09-15", + "deprecation_date": "2026-09-14", "input_cost_per_token": 2e-08, "litellm_provider": "together_ai", "max_input_tokens": 514, @@ -45680,7 +45682,7 @@ "supports_tool_choice": true }, "together_ai/thinkingmachines/Inkling-Small": { - "deprecation_date": "2026-09-15", + "deprecation_date": "2026-09-14", "cache_read_input_token_cost": 1e-07, "input_cost_per_token": 5e-07, "litellm_provider": "together_ai", @@ -50573,7 +50575,7 @@ "wandb/openai/gpt-oss-120b": { "supports_reasoning": true, "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, "output_cost_per_token": 1.7e-07, @@ -50584,7 +50586,7 @@ "wandb/openai/gpt-oss-20b": { "supports_reasoning": true, "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "max_output_tokens": 131072, "input_cost_per_token": 3e-08, "output_cost_per_token": 1.3e-07, @@ -50593,6 +50595,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/zai-org/GLM-4.5": { + "deprecation_date": "2026-03-04", "supports_reasoning": true, "max_tokens": 131072, "max_input_tokens": 131072, @@ -50603,6 +50606,7 @@ "mode": "chat" }, "wandb/Qwen/Qwen3-235B-A22B-Instruct-2507": { + "deprecation_date": "2026-08-04", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -50612,6 +50616,7 @@ "mode": "chat" }, "wandb/Qwen/Qwen3-Coder-480B-A35B-Instruct": { + "deprecation_date": "2026-08-25", "max_tokens": 262144, "max_input_tokens": 262144, "max_output_tokens": 262144, @@ -50622,6 +50627,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3-235B-A22B-Thinking-2507": { + "deprecation_date": "2026-08-04", "supports_reasoning": true, "max_tokens": 262144, "max_input_tokens": 262144, @@ -50632,6 +50638,7 @@ "mode": "chat" }, "wandb/moonshotai/Kimi-K2-Instruct": { + "deprecation_date": "2026-03-04", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -50656,6 +50663,7 @@ "supports_vision": true }, "wandb/MiniMaxAI/MiniMax-M2.5": { + "deprecation_date": "2026-08-25", "max_tokens": 197000, "max_input_tokens": 197000, "max_output_tokens": 197000, @@ -50670,7 +50678,7 @@ }, "wandb/meta-llama/Llama-3.1-8B-Instruct": { "max_tokens": 128000, - "max_input_tokens": 128000, + "max_input_tokens": 131000, "max_output_tokens": 128000, "input_cost_per_token": 2.2e-07, "output_cost_per_token": 2.2e-07, @@ -50690,6 +50698,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/deepseek-ai/DeepSeek-R1-0528": { + "deprecation_date": "2026-03-04", "supports_reasoning": true, "max_tokens": 161000, "max_input_tokens": 161000, @@ -50700,6 +50709,7 @@ "mode": "chat" }, "wandb/deepseek-ai/DeepSeek-V3-0324": { + "deprecation_date": "2026-03-04", "max_tokens": 161000, "max_input_tokens": 161000, "max_output_tokens": 161000, @@ -50719,6 +50729,7 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/meta-llama/Llama-4-Scout-17B-16E-Instruct": { + "deprecation_date": "2026-04-21", "max_tokens": 64000, "max_input_tokens": 64000, "max_output_tokens": 64000, @@ -50728,6 +50739,7 @@ "mode": "chat" }, "wandb/microsoft/Phi-4-mini-instruct": { + "deprecation_date": "2026-08-04", "max_tokens": 128000, "max_input_tokens": 128000, "max_output_tokens": 128000, @@ -56692,7 +56704,8 @@ "supports_function_calling": true, "supports_vision": true, "supports_web_search": true, - "gemini_audio_only_live": true + "gemini_audio_only_live": true, + "supports_response_schema": false }, "gemini-3.8-live-extended-thinking": { "input_cost_per_audio_token": 3e-06, @@ -56726,7 +56739,8 @@ "supports_vision": true, "supports_web_search": true, "gemini_audio_only_live": true, - "supports_reasoning": true + "supports_reasoning": true, + "supports_response_schema": false }, "gemini/gemini-2.5-flash-native-audio-latest": { "input_cost_per_audio_token": 3e-06, @@ -60970,10 +60984,11 @@ "wandb/deepseek-ai/DeepSeek-V4-Flash": { "supports_reasoning": true, "max_tokens": 1048576, - "max_input_tokens": 1048576, + "max_input_tokens": 1049000, "input_cost_per_token": 1.4e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 7e-08, + "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -60983,7 +60998,7 @@ "wandb/deepseek-ai/DeepSeek-V4-Flash-0731": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 1.3e-07, "output_cost_per_token": 2.8e-07, "cache_read_input_token_cost": 7e-08, @@ -60996,10 +61011,11 @@ "wandb/deepseek-ai/DeepSeek-V4-Pro": { "supports_reasoning": true, "max_tokens": 1048576, - "max_input_tokens": 1048576, + "max_input_tokens": 1049000, "input_cost_per_token": 1.15e-06, "output_cost_per_token": 2.55e-06, "cache_read_input_token_cost": 2e-07, + "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -61009,7 +61025,7 @@ "wandb/google/gemma-4-31B-it": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3.4e-07, "litellm_provider": "wandb", @@ -61018,8 +61034,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/ibm-granite/granite-4.1-8b": { + "deprecation_date": "2026-10-05", "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, "litellm_provider": "wandb", @@ -61028,8 +61045,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/JetBrains/Mellum2-12B-A2.5B-Instruct": { + "deprecation_date": "2026-10-05", "max_tokens": 131072, - "max_input_tokens": 131072, + "max_input_tokens": 131000, "input_cost_per_token": 5e-08, "output_cost_per_token": 1e-07, "litellm_provider": "wandb", @@ -61038,8 +61056,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/meta-llama/Llama-3.1-70B-Instruct": { + "deprecation_date": "2026-10-05", "max_tokens": 128000, - "max_input_tokens": 128000, + "max_input_tokens": 131000, "input_cost_per_token": 8e-07, "output_cost_per_token": 8e-07, "litellm_provider": "wandb", @@ -61050,7 +61069,7 @@ "wandb/MiniMaxAI/MiniMax-M3": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 2.3e-07, "output_cost_per_token": 9.6e-07, "cache_read_input_token_cost": 5e-08, @@ -61063,7 +61082,7 @@ "wandb/moonshotai/Kimi-K2.7-Code": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 7.1e-07, "output_cost_per_token": 3.5e-06, "cache_read_input_token_cost": 1.5e-07, @@ -61076,7 +61095,7 @@ "wandb/moonshotai/Kimi-K2.6": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 6.5e-07, "output_cost_per_token": 3.41e-06, "cache_read_input_token_cost": 1.5e-07, @@ -61089,10 +61108,10 @@ "wandb/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, - "input_cost_per_token": 1e-07, - "output_cost_per_token": 2.5e-07, - "cache_read_input_token_cost": 5e-08, + "max_input_tokens": 262000, + "input_cost_per_token": 7e-08, + "output_cost_per_token": 2e-07, + "cache_read_input_token_cost": 4e-08, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -61102,10 +61121,10 @@ "wandb/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, - "input_cost_per_token": 7.5e-07, - "output_cost_per_token": 2.75e-06, - "cache_read_input_token_cost": 1.5e-07, + "max_input_tokens": 262000, + "input_cost_per_token": 5e-07, + "output_cost_per_token": 2.15e-06, + "cache_read_input_token_cost": 1e-07, "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -61113,8 +61132,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/OpenPipe/Qwen3-14B-Instruct": { + "deprecation_date": "2026-10-05", "max_tokens": 32768, - "max_input_tokens": 32768, + "max_input_tokens": 32800, "input_cost_per_token": 5e-08, "output_cost_per_token": 2.2e-07, "litellm_provider": "wandb", @@ -61125,7 +61145,7 @@ "wandb/Qwen/Qwen3.8-27B": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 4e-07, "output_cost_per_token": 3e-06, "cache_read_input_token_cost": 1.5e-07, @@ -61138,7 +61158,7 @@ "wandb/Qwen/Qwen3.6-35B-A3B": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, "litellm_provider": "wandb", @@ -61149,10 +61169,11 @@ "wandb/Qwen/Qwen3.6-27B": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 6e-07, "output_cost_per_token": 3.6e-06, "cache_read_input_token_cost": 1.2e-07, + "deprecation_date": "2026-10-05", "supports_prompt_caching": true, "litellm_provider": "wandb", "mode": "chat", @@ -61160,9 +61181,10 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3.5-35B-A3B": { + "deprecation_date": "2026-10-05", "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 2.5e-07, "output_cost_per_token": 1.25e-06, "litellm_provider": "wandb", @@ -61171,8 +61193,9 @@ "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/Qwen/Qwen3-30B-A3B-Instruct-2507": { + "deprecation_date": "2026-10-05", "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 262000, "input_cost_per_token": 1e-07, "output_cost_per_token": 3e-07, "litellm_provider": "wandb", @@ -61187,6 +61210,7 @@ "input_cost_per_token": 1.31e-06, "output_cost_per_token": 3.96e-06, "cache_read_input_token_cost": 4.4e-08, + "max_input_tokens": 1049000, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/" }, @@ -61197,13 +61221,14 @@ "input_cost_per_token": 1e-07, "output_cost_per_token": 1.5e-07, "cache_read_input_token_cost": 5e-08, + "max_input_tokens": 131000, "supports_prompt_caching": true, "source": "https://wandb.ai/site/pricing/tokens/" }, "wandb/zai-org/GLM-5.2": { "supports_reasoning": true, "max_tokens": 262144, - "max_input_tokens": 262144, + "max_input_tokens": 1049000, "input_cost_per_token": 7.6e-07, "output_cost_per_token": 2.42e-06, "cache_read_input_token_cost": 1.4e-07, @@ -62866,7 +62891,7 @@ "max_tokens": 1048576, "mode": "chat", "output_cost_per_token": 6.6e-06, - "source": "https://docs.fireworks.ai/serverless/pricing", + "source": "https://api.fireworks.ai/v1/serverless/models", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, @@ -69158,5 +69183,19 @@ "supports_prompt_caching": true, "supports_reasoning": true, "supports_vision": true + }, + "wandb/zai-org/GLM-5.3-Flash": { + "cache_read_input_token_cost": 5e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "wandb", + "max_input_tokens": 1049000, + "mode": "chat", + "output_cost_per_token": 5e-07, + "source": "https://wandb.ai/site/pricing/tokens/", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true } }