grok-4.7

Description

xAI Grok 4.7 — a frontier model built for coding, agentic tasks, and knowledge work. It accepts text and image input and has a 500,000-token context window. Reasoning cannot be turned off: reasoning_effort selects low, medium, high, or xhigh, with high as the default, and reasoning tokens are billed as output. When a prompt reaches 200,000 tokens, every token in that request is billed at the long-context rate. Only function tools are accepted; xAI's server-side tools, such as web search, X search, and code execution, are not available, and requests that include them are refused. On /v1/responses, send the whole conversation in the input array on every turn and pass back the encrypted reasoning items from earlier responses unchanged; requests that carry previous_response_id or conversation are refused.