From 3e2dcc9c784216d9daa8d7fb31ec41ca8a8e666d Mon Sep 17 00:00:00 2001 From: Ted Slesinski Date: Sat, 12 Jul 2025 09:42:29 -0400 Subject: [PATCH] Update docs for grok 4 --- README.md | 1 + docs/advanced-usage.md | 5 +++++ docs/configuration.md | 9 ++++++--- 3 files changed, 12 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index d7b516c..f2bc0ba 100644 --- a/README.md +++ b/README.md @@ -290,6 +290,7 @@ nano .env # The file will contain, at least one should be set: # GEMINI_API_KEY=your-gemini-api-key-here # For Gemini models # OPENAI_API_KEY=your-openai-api-key-here # For O3 model +# XAI_API_KEY=your-xai-api-key-here # For Grok models # OPENROUTER_API_KEY=your-openrouter-key # For OpenRouter (see docs/custom_models.md) # DIAL_API_KEY=your-dial-api-key-here # For DIAL platform diff --git a/docs/advanced-usage.md b/docs/advanced-usage.md index 9383354..63856da 100644 --- a/docs/advanced-usage.md +++ b/docs/advanced-usage.md @@ -39,6 +39,9 @@ Regardless of your default configuration, you can specify models per request: | **`o3-mini`** | OpenAI | 200K tokens | Balanced speed/quality | Moderate complexity tasks | | **`o4-mini`** | OpenAI | 200K tokens | Latest reasoning model | Optimized for shorter contexts | | **`gpt4.1`** | OpenAI | 1M tokens | Latest GPT-4 with extended context | Large codebase analysis, comprehensive reviews | +| **`grok-4-latest`** | X.AI | 256K tokens | Latest flagship model with reasoning, vision | Complex analysis, reasoning tasks | +| **`grok-3`** | X.AI | 131K tokens | Advanced reasoning model | Deep analysis, complex problems | +| **`grok-3-fast`** | X.AI | 131K tokens | Higher performance variant | Fast responses with reasoning | | **`llama`** (Llama 3.2) | Custom/Local | 128K tokens | Local inference, privacy | On-device analysis, cost-free processing | | **Any model** | OpenRouter | Varies | Access to GPT-4, Claude, Llama, etc. | User-specified or based on task requirements | @@ -49,6 +52,8 @@ cloud models (expensive/powerful) AND local models (free/private) in the same co - **Gemini Models**: Support thinking modes (minimal to max), web search, 1M context - **O3 Models**: Excellent reasoning, systematic analysis, 200K context - **GPT-4.1**: Extended context window (1M tokens), general capabilities +- **Grok-4**: Extended thinking support, vision capabilities, 256K context +- **Grok-3 Models**: Advanced reasoning, 131K context ## Model Usage Restrictions diff --git a/docs/configuration.md b/docs/configuration.md index 473b6de..12e9d65 100644 --- a/docs/configuration.md +++ b/docs/configuration.md @@ -74,7 +74,8 @@ DEFAULT_MODEL=auto # Claude picks best model for each task (recommended) - **`o3`**: Strong logical reasoning (200K context) - **`o3-mini`**: Balanced speed/quality (200K context) - **`o4-mini`**: Latest reasoning model, optimized for shorter contexts -- **`grok`**: GROK-3 advanced reasoning (131K context) +- **`grok-3`**: GROK-3 advanced reasoning (131K context) +- **`grok-4-latest`**: GROK-4 latest flagship model (256K context) - **Custom models**: via OpenRouter or local APIs ### Thinking Mode Configuration @@ -107,7 +108,7 @@ OPENAI_ALLOWED_MODELS=o3-mini,o4-mini,mini GOOGLE_ALLOWED_MODELS=flash,pro # X.AI GROK model restrictions -XAI_ALLOWED_MODELS=grok-3,grok-3-fast +XAI_ALLOWED_MODELS=grok-3,grok-3-fast,grok-4-latest # OpenRouter model restrictions (affects models via custom provider) OPENROUTER_ALLOWED_MODELS=opus,sonnet,mistral @@ -128,9 +129,11 @@ OPENROUTER_ALLOWED_MODELS=opus,sonnet,mistral - `pro` (shorthand for Pro model) **X.AI GROK Models:** +- `grok-4-latest` (256K context, latest flagship model with reasoning, vision, and structured outputs) - `grok-3` (131K context, advanced reasoning) - `grok-3-fast` (131K context, higher performance) -- `grok` (shorthand for grok-3) +- `grok` (shorthand for grok-4-latest) +- `grok4` (shorthand for grok-4-latest) - `grok3` (shorthand for grok-3) - `grokfast` (shorthand for grok-3-fast)