xAI Grok 4.7

Grok 4.7 (xai.grok-4.7) is a reasoning model designed for coding, agentic tasks, and knowledge work. The model supports long-running coding tasks, document and presentation creation, and workflows that require checking intermediate results. It has a 500,000-token context window.

Learn about Grok 4.7.

Regions for this Model

Important

For supported regions, endpoint types (on-demand or dedicated AI clusters), and hosting (OCI Generative AI or external calls) for this model, see the Models by Region page. For details about the regions, see the Generative AI Regions page.

Access this Model

Access this model on demand through supported text API requests in the supported regions.

Key Features

  • Model name in OCI Generative AI: xai.grok-4.7
  • Available On-Demand: Access this model on demand through supported text API requests.
  • Context Length: 500,000 tokens.
  • Reasoning: Supports low, medium, high (default), and xhigh effort levels. Reasoning can't be disabled. Higher effort levels can increase response time.
  • Function Calling: Supports calls to external tools.
  • Structured Outputs: Supports responses that follow a specified format.
  • Cached Input Tokens: Yes. For the number of cached input tokens, see the cachedTokens attribute in PromptTokensDetails Reference API and for prices, see the Pricing Page.
  • Knowledge Cutoff: May 2026.

For model capabilities and reasoning behavior, see the xAI documentation for Grok 4.7 and Reasoning.

On-Demand Mode

Note

The Grok models are available only in the on-demand mode.
Model Name OCI Model Name
xAI Grok 4.7 xai.grok-4.7

Pricing

Grok 4.7 has different rates for short- and long-context requests. Input tokens, cached input tokens, and output tokens are priced separately.

For current rates, see the OCI Pricing Page. On that page, search for Generative AI, then find the Grok 4.7 entries.