MODELS

SpaceXAI: Grok 4.7

by xAI

xAIGrokagents

Overview

xAI frontier model for coding, agentic tasks, and knowledge work.

Details

Grok 4.7 is an xAI frontier model available through the Grok API. xAI describes it as a model for coding, agentic tasks, and knowledge work, with particular strength in long-running software-engineering tasks and verifying its own work. The official model documentation identifies the API model name as `grok-4.7`, lists input, cached-input, and output token pricing, and documents support for structured outputs and reasoning efforts. xAI also provides a model card covering capabilities, limitations, safety evaluations, safeguards, and intended use.

When to Use

Use for long-running software-engineering and coding tasks. Use for agentic workflows and knowledge-work applications. Use when structured outputs or configurable reasoning effort are needed through the Grok API.

Getting Started

Review the Grok 4.7 model documentation and API examples.
Select `grok-4.7` when making Grok API requests.
Review the published input
cached-input
and output token pricing before estimating costs.
Evaluate the model on representative coding or agentic workloads before deploying it.

Key Features

•Frontier model for coding
•agentic tasks
•and knowledge work.
•Designed for long-running software-engineering work and self-verification.
•Available through the Grok API as `grok-4.7`.
•Supports structured outputs and reasoning efforts.
•Official model card documents capabilities
•limitations
•and safety evaluations.

Capabilities

•coding
•agentic tasks
•knowledge work
•software engineering
•structured outputs
•reasoning efforts

Last updated Sep 24, 2026