Grok 4.7

Grok 4.7 is SpaceXAI's frontier model for coding, agentic tasks, and knowledge work, with native training for the Grok Bot harness.

Language ModelCoding AssistantAgent WorkflowsVision InputTool UseSpaceXAI

SpaceXAI API / Grok Build / Cursor / supported gateways

Below 200K prompt tokens: $2/1M input, $0.50 cached input, $6 output; above 200K: $4/$1/$12; Fast is product-only at 2x

Commercial

🚀Function Overview

Grok 4.7 keeps Grok 4.6's public API limits and prices while moving to a larger base model and longer reinforcement-learning run.

Key Features

Official SpaceXAI API model ID grok-4.7
500,000-token context window and no documented text-output limit
Text and image input with text output
Low, medium, high default, and xhigh reasoning effort
$2 input, $0.50 cached input, and $6 output per million tokens below 200K prompt tokens
$4 input, $1 cached input, and $12 output per million tokens above 200K prompt tokens
Responses API always returns reasoning.encrypted_content
Grok 4.7 Fast is available through Cursor and Grok Build at twice the token rates, not on the public SpaceXAI API

Use Cases

•Repository coding agents
•Long-running knowledge-work agents
•Grok Bot workflows
•Image-assisted analysis
•Routing through Cursor, Grok Build, or the public API

⚙️Input Parameters

model

string

Use grok-4.7 on the public SpaceXAI API.

input

object

Text or supported image input.

reasoning_effort

string

Choose low, medium, high, or xhigh; high is the documented default.

tools

array

Optional tools supported by the active API or product surface.

💡Usage Examples

Example 1

Input Parameters

{
  "model": "grok-4.7",
  "input": "Investigate this repository, implement the requested feature, and verify it.",
  "reasoning_effort": "high"
}

Output Results

Grok 4.7 returns text plus encrypted reasoning metadata on the Responses API. Measure task success, review cost, and threshold pricing before migration.

Quick Actions

Technical Specifications

Hardware Type: SpaceXAI API / Grok Build / Cursor / supported gateways
Commercial Use: Supported
Pricing: Below 200K prompt tokens: $2/1M input, $0.50 cached input, $6 output; above 200K: $4/$1/$12; Fast is product-only at 2x