From 1c65800f4a282b12a62f87bb892b0d41e3d00a10 Mon Sep 17 00:00:00 2001 From: Cesar Garcia <128240629+Chesars@users.noreply.github.com> Date: Fri, 21 Nov 2025 20:57:55 -0300 Subject: [PATCH] Feat: add support for Grok 4.1 Fast models (#16936) * feat: Add support for Grok 4.1 Fast models Add new xAI Grok 4.1 Fast models optimized for high-performance agentic tool calling: - xai/grok-4-1-fast (alias for grok-4-1-fast-reasoning) - xai/grok-4-1-fast-reasoning (with reasoning capabilities) - xai/grok-4-1-fast-reasoning-latest - xai/grok-4-1-fast-non-reasoning (without reasoning for faster responses) - xai/grok-4-1-fast-non-reasoning-latest Features: - Context window: 2,000,000 tokens - Pricing: $0.20/1M input, $0.50/1M output tokens - Cached tokens: $0.05/1M tokens - Supports: Function calling, Structured outputs, Vision, Audio input, Web search, Reasoning Fixes #16927 * docs: Add comprehensive Grok models documentation - Add 'Supported Models' section highlighting new Grok 4.1 Fast models - Include comparison guide for reasoning vs non-reasoning models - Add complete model family table (Grok 4.1, 4, 3, Code, 2) - Add features legend explaining capabilities - Remove pricing details (link to xAI docs instead for current rates) - Improve documentation clarity and consistency Related to #16927 * docs: Minor corrections to xai.md --- docs/my-website/docs/providers/xai.md | 62 +++++++++++++++++ model_prices_and_context_window.json | 98 +++++++++++++++++++++++++++ 2 files changed, 160 insertions(+) diff --git a/docs/my-website/docs/providers/xai.md b/docs/my-website/docs/providers/xai.md index 49a3640991..afeecc2152 100644 --- a/docs/my-website/docs/providers/xai.md +++ b/docs/my-website/docs/providers/xai.md @@ -11,6 +11,68 @@ https://docs.x.ai/docs ::: +## Supported Models + + + +**Latest Release** - Grok 4.1 Fast: Optimized for high-performance agentic tool calling with 2M context and prompt caching. + +| Model | Context | Features | +|-------|---------|----------| +| `xai/grok-4-1-fast-reasoning` | 2M tokens | **Reasoning**, Function calling, Vision, Audio, Web search, Caching | +| `xai/grok-4-1-fast-non-reasoning` | 2M tokens | Function calling, Vision, Audio, Web search, Caching | + +**When to use:** +- ✅ **Reasoning model**: Complex analysis, planning, multi-step reasoning problems +- ✅ **Non-reasoning model**: Simple queries, faster responses, lower token usage + +**Example:** +```python +from litellm import completion + +# With reasoning +response = completion( + model="xai/grok-4-1-fast-reasoning", + messages=[{"role": "user", "content": "Analyze this problem step by step..."}] +) + +# Without reasoning +response = completion( + model="xai/grok-4-1-fast-non-reasoning", + messages=[{"role": "user", "content": "What's 2+2?"}] +) +``` + +--- + +### All Available Models + +| Model Family | Model | Context | Features | +|--------------|-------|---------|----------| +| **Grok 4.1** | `xai/grok-4-1-fast-reasoning` | 2M | **Reasoning**, Tools, Vision, Audio, Web search, Caching | +| | `xai/grok-4-1-fast-non-reasoning` | 2M | Tools, Vision, Audio, Web search, Caching | +| **Grok 4** | `xai/grok-4` | 256K | Tools, Web search | +| | `xai/grok-4-0709` | 256K | Tools, Web search | +| | `xai/grok-4-fast-reasoning` | 2M | **Reasoning**, Tools, Web search | +| | `xai/grok-4-fast-non-reasoning` | 2M | Tools, Web search | +| **Grok 3** | `xai/grok-3` | 131K | Tools, Web search | +| | `xai/grok-3-mini` | 131K | Tools, Web search | +| | `xai/grok-3-fast-beta` | 131K | Tools, Web search | +| **Grok Code** | `xai/grok-code-fast` | 256K | **Reasoning**, Tools, Code generation, Caching | +| **Grok 2** | `xai/grok-2` | 131K | Tools, **Vision** | +| | `xai/grok-2-vision-latest` | 32K | Tools, **Vision** | + +**Features:** +- **Reasoning** = Chain-of-thought reasoning with reasoning tokens +- **Tools** = Function calling / Tool use +- **Web search** = Live internet search +- **Vision** = Image understanding +- **Audio** = Audio input support +- **Caching** = Prompt caching for cost savings +- **Code generation** = Optimized for code tasks + +**Pricing:** See [xAI's pricing page](https://docs.x.ai/docs/models) for current rates. + ## API Key ```python # env variable diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 43c9c05030..fb3d4c9171 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -26179,6 +26179,104 @@ "supports_tool_choice": true, "supports_web_search": true }, + "xai/grok-4-1-fast": { + "cache_read_input_token_cost": 0.05e-06, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, + "litellm_provider": "xai", + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, + "mode": "chat", + "output_cost_per_token": 0.5e-06, + "output_cost_per_token_above_128k_tokens": 1e-06, + "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-4-1-fast-reasoning": { + "cache_read_input_token_cost": 0.05e-06, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, + "litellm_provider": "xai", + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, + "mode": "chat", + "output_cost_per_token": 0.5e-06, + "output_cost_per_token_above_128k_tokens": 1e-06, + "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-4-1-fast-reasoning-latest": { + "cache_read_input_token_cost": 0.05e-06, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, + "litellm_provider": "xai", + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, + "mode": "chat", + "output_cost_per_token": 0.5e-06, + "output_cost_per_token_above_128k_tokens": 1e-06, + "source": "https://docs.x.ai/docs/models/grok-4-1-fast-reasoning", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-4-1-fast-non-reasoning": { + "cache_read_input_token_cost": 0.05e-06, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, + "litellm_provider": "xai", + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, + "mode": "chat", + "output_cost_per_token": 0.5e-06, + "output_cost_per_token_above_128k_tokens": 1e-06, + "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, + "xai/grok-4-1-fast-non-reasoning-latest": { + "cache_read_input_token_cost": 0.05e-06, + "input_cost_per_token": 0.2e-06, + "input_cost_per_token_above_128k_tokens": 0.4e-06, + "litellm_provider": "xai", + "max_input_tokens": 2e6, + "max_output_tokens": 2e6, + "max_tokens": 2e6, + "mode": "chat", + "output_cost_per_token": 0.5e-06, + "output_cost_per_token_above_128k_tokens": 1e-06, + "source": "https://docs.x.ai/docs/models/grok-4-1-fast-non-reasoning", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true + }, "xai/grok-beta": { "input_cost_per_token": 5e-06, "litellm_provider": "xai",