From cb385e080f41af040e86ecf79006ec914c5d2304 Mon Sep 17 00:00:00 2001 From: Ishaan Jaff Date: Sat, 4 Oct 2025 14:50:44 -0700 Subject: [PATCH] Fix "azure_ai/grok-4-fast-reasoning" entry in "model_prices_and_context_window.json" (#15204) * fix: azure_ai/grok-4-fast-non-reasoning * fix pricing --- docs/my-website/release_notes/v1.77.7-stable/index.md | 4 ++-- litellm/model_prices_and_context_window_backup.json | 11 +++++------ model_prices_and_context_window.json | 11 +++++------ 3 files changed, 12 insertions(+), 14 deletions(-) diff --git a/docs/my-website/release_notes/v1.77.7-stable/index.md b/docs/my-website/release_notes/v1.77.7-stable/index.md index 658a9c3441..b689996b79 100644 --- a/docs/my-website/release_notes/v1.77.7-stable/index.md +++ b/docs/my-website/release_notes/v1.77.7-stable/index.md @@ -75,8 +75,8 @@ pip install litellm==1.77.7.rc.1 | Anthropic | `claude-sonnet-4-5-20250929` | 200K | $3.00 | $15.00 | Chat, reasoning, vision, function calling, prompt caching | | Bedrock | `eu.anthropic.claude-sonnet-4-5-20250929-v1:0` | 200K | $3.00 | $15.00 | Chat, reasoning, vision, function calling, prompt caching | | Azure AI | `azure_ai/grok-4` | 131K | $5.50 | $27.50 | Chat, reasoning, function calling, web search | -| Azure AI | `azure_ai/grok-4-fast-reasoning` | 131K | $5.80 | $2,900.00 | Chat, reasoning, function calling, web search | -| Azure AI | `azure_ai/grok-4-fast-non-reasoning` | 131K | $5.00 | $2,500.00 | Chat, function calling, web search | +| Azure AI | `azure_ai/grok-4-fast-reasoning` | 131K | $0.43 | $1.73 | Chat, reasoning, function calling, web search | +| Azure AI | `azure_ai/grok-4-fast-non-reasoning` | 131K | $0.43 | $1.73 | Chat, function calling, web search | | Azure AI | `azure_ai/grok-code-fast-1` | 131K | $3.50 | $17.50 | Chat, function calling, web search | | Groq | `groq/moonshotai/kimi-k2-instruct-0905` | Context varies | Pricing varies | Pricing varies | Chat, function calling | | Ollama | Ollama Cloud models | Varies | Free | Free | Self-hosted models via Ollama Cloud | diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 72b9c551d7..7ed04dc79c 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3324,28 +3324,27 @@ "supports_web_search": true }, "azure_ai/grok-4-fast-non-reasoning": { - "input_cost_per_token": 5e-06, + "input_cost_per_token": 0.43e-06, + "output_cost_per_token": 1.73e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-03, - "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/grok-4-fast-reasoning": { - "input_cost_per_token": 5.8e-06, + "input_cost_per_token": 0.43e-06, + "output_cost_per_token": 1.73e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.9e-03, - "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/", + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/announcing-the-grok-4-fast-models-from-xai-now-available-in-azure-ai-foundry/4456701", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 72b9c551d7..7ed04dc79c 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3324,28 +3324,27 @@ "supports_web_search": true }, "azure_ai/grok-4-fast-non-reasoning": { - "input_cost_per_token": 5e-06, + "input_cost_per_token": 0.43e-06, + "output_cost_per_token": 1.73e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.5e-03, - "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/", "supports_function_calling": true, "supports_response_schema": true, "supports_tool_choice": true, "supports_web_search": true }, "azure_ai/grok-4-fast-reasoning": { - "input_cost_per_token": 5.8e-06, + "input_cost_per_token": 0.43e-06, + "output_cost_per_token": 1.73e-06, "litellm_provider": "azure_ai", "max_input_tokens": 131072, "max_output_tokens": 131072, "max_tokens": 131072, "mode": "chat", - "output_cost_per_token": 2.9e-03, - "source": "https://azure.microsoft.com/en-us/blog/grok-4-is-now-available-in-azure-ai-foundry-unlock-frontier-intelligence-and-business-ready-capabilities/", + "source": "https://techcommunity.microsoft.com/blog/azure-ai-foundry-blog/announcing-the-grok-4-fast-models-from-xai-now-available-in-azure-ai-foundry/4456701", "supports_function_calling": true, "supports_reasoning": true, "supports_response_schema": true,