Skip to main content

Command Palette

Search for a command to run...

Models
Cursor

Grok 4.7

Model ID
grok-4.7
Context window
256k
Max context
500k
Provider
Cursor
Capabilities
AgentThinking
Speed
Medium
Cost
Medium
Intelligence
Frontier

Grok 4.7 is a frontier model from Cursor and SpaceXAI for coding and knowledge work. It builds on Grok 4.6 with a larger base, longer training on harder multi-hour tasks, and stronger self-verification.

Strengths

  • Stays with difficult, long-running work and checks its own results more carefully than Grok 4.6.
  • Manages longer context more reliably, with a 256k standard window and 500k long context.
  • Stronger on complex coding and multi-hour knowledge work.

Effort levels

Grok 4.7 supports four effort levels: xhigh, high (default), medium, and low. Higher effort gives the model more time to work through difficult tasks. Effort levels are more separated than in Grok 4.6, so harder tasks spend more time thinking.

Fast is the default speed tier on Pro and higher plans. On the Start plan (India only), Grok 4.7 is fixed at medium effort at standard speed.

Tools

Grok 4.7 has access to all agent tools when used with Cursor, including:

Find files by name, read directory structures, and grep for patterns.

Generate search queries and fetch results from the web.

Read file contents, including images for vision-capable models.

Suggest edits and apply them automatically.

Execute terminal commands and monitor output.

Control a browser to take screenshots, test applications, and verify visual changes. See the Browser documentation.

Generate images from text descriptions or reference images.

Ask clarifying questions while continuing to work in the background.

Retrieve rules based on type and description.

Learn more about how tools work and tool calling fundamentals.

Pricing

Grok 4.7 is part of the Cursor Models pool on individual and team plans. This pool also includes Grok 4.6, Grok 4.5, and Composer 2.5.

Standard on-demand usage is priced at $2/M input tokens, $0.50/M cached input tokens, and $6/M output tokens. Fast is $4/M input, $1/M cached, and $12/M output. When input exceeds 256k tokens, standard requests bill at 2x those rates and Fast requests bill at 3x the standard rates, up to a 500k context window. Long-context billing uses the input length only: if input is at or below 256k tokens, the full request uses the standard or Fast rates. All prices are per million tokens.

Name
$2-$0.5$6
$4-$1$12
$4-$1$12
$6-$1.5$18