Skip to content

Grok 4.7

xAI's flagship Grok model for code and agentic tool calling, with 500K-token context.

By xAIsource

Facts read from official pages, last on

Official page

Price

What the gateway charges per million tokens: what you send in, and what the model writes back.

Source: Vercel AI Gateway, checked 2026-09-25.

Input
$1.20per 1M tokens
Output
$3.60per 1M tokensOutput costs 3x the input.

Above 200,000 input tokens: $2.4 in, $7.2 out per 1M.

Specs

How much it reads at once, how much it writes back, and how recent its knowledge is.

Source: Vercel AI Gateway, checked 2026-09-25.

Context window
500K tokens500,000
Max output
500K tokens500,000
Knowledge cutoff
May 2026
Released
Type
Language
Modalities
Takes text, image. Returns text.
Gateway ID
spacexai/grok-4.7

Capabilities

What the gateway says this model supports.

Source: Vercel AI Gateway, checked 2026-09-25.

  • Reasoning
  • Tool use
  • Implicit caching
  • Vision
  • Structured output

Data handling

What happens to your prompts, and what you have to switch on.

Source: Vercel AI Gateway, checked 2026-09-25.

ZDREvery provider

Zero data retention

Available on a paid Vercel plan through the AI Gateway, from every provider on it (you turn it on).

NTEvery provider

No training on prompts

Offered by every provider on the Vercel AI Gateway, when you turn it on.

Usage

How much people actually run it, as counted where it is served.

requests
3.4M3,354,539 requests
tokens
197.3B197,334,220,794 tokens

Counted on OpenRouter over the 5 days to 2026-09-25.

Also by xAI1

Friday

The brief, by email

Five to seven links an issue, each with what to do about it.

Unsubscribe from any issue.

This page as Markdown