ModelBeat
Models/Grok 4.7
All models
X
x-ai/grok-4.7

Grok 4.7 is xAI’s proprietary AI model, released Sep 21, 2026. It costs $1.60/M input and $4.80/M output tokens, and handles a 500K-token context window. Its strongest use case is coding, where it ranks in the 92nd percentile of the models Model Beat tracks.

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6.

Context
500K
Input
$1.60 / 1M
Output
$4.80 / 1M
Released
Sep 21, 2026
Modalities
textimagefiletext
Strongest atCoding top 8%Reasoning & Knowledge top 14%

Benchmarks

Scores on standardized evaluations. Higher is better — and rank shows where Grok 4.7 lands among all models tracked on Model Beat.

89.0
Intelligence Index
Artificial Analysis
89th percentile of tracked models
92.0
Coding Index
Artificial Analysis
92nd percentile of tracked models

Reasoning

1 evals
Humanity's Last Exam43.1%

Frontier of human expert knowledge

Coding

1 evals
SciCode57.4%

Scientific research coding

In the news

2

Compare Grok 4.7 with

Frequently asked questions

What is Grok 4.7?

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6.

Who created Grok 4.7?

Grok 4.7 is an AI model developed by xAI, part of the Grok family, released Sep 21, 2026.

How much does Grok 4.7 cost?

Grok 4.7's list price from xAI is $1.60 per million input tokens and $4.80 per million output tokens.

What is Grok 4.7's context window?

Grok 4.7 supports a context window of up to 500K tokens.

How does Grok 4.7 perform on benchmarks?

On standardized evaluations tracked by Epoch AI, Grok 4.7 scores 57.4% on SciCode, 43.1% on Humanity's Last Exam.

Is Grok 4.7 open source?

Grok 4.7 is a proprietary model (API access), available through its provider's API rather than as a downloadable open-weight model.

Benchmark data from Epoch AI (CC BY) and Artificial Analysis; pricing, specs & descriptions from OpenRouter. Data updated Sep 22, 2026.