Grok 4.7

About Grok 4.7

Grok 4.7 is xAI's frontier model for coding, agentic tasks and knowledge work. Released on September 21, 2026, it uses a new and larger base model than Grok 4.6 and was trained with a longer reinforcement learning run focused on difficult tasks that can require extended execution and verification.

The model supports text and image inputs and produces text output. It has a 500,000 token context window, a May 2026 knowledge cutoff and no documented text output limit. Grok 4.7 supports configurable reasoning effort with low, medium, high and xhigh settings.

Developers can use Grok 4.7 through the xAI Responses API and Chat Completions API. Supported tools documented specifically for the model include function calling, web search, X search and code execution. Image understanding allows applications to submit images through public URLs or base64 encoded image data together with text prompts.

Grok 4.7 is available through the xAI API, Grok Build and Cursor, as well as model gateways including OpenRouter, Vercel and Cloudflare. A US regional API endpoint is also available for workloads requiring inference to remain in the United States.

Key Features

• Multimodal Input: Accepts both text and image inputs while generating text output.
• 500K Context Window: Supports a context window of up to 500,000 tokens for long prompts and agent workflows.
• Configurable Reasoning: Supports low, medium, high and xhigh reasoning effort levels.
• Tool Calling: Supports function calling, web search, X search and code execution.
• Coding and Agentic Tasks: Designed for coding, extended agent workflows and knowledge work.
• API Access: Available through the xAI Responses API and Chat Completions API with support for the xAI SDK and compatible development libraries.