xAIactive

Grok 4.7

Released at: September 21, 2026

API StatusAvailable for integration
Context Window500,000 tokens(heuristic estimate)
Input Price / MTok$2.00(heuristic estimate)
Output Price / MTok$6.00(heuristic estimate)

Model Overview

xAI · Active Model

  • Long-Context
  • API Available
  • Reported Benchmarks

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

Developer
xAI(heuristic estimate)
Release Date
September 21, 2026(heuristic estimate)
Context Window
500,000 tokens≈ 667 words(heuristic estimate)
API Access
Publicly AvailableIntegrate via official API(heuristic estimate)
Input Cost
$2.00per million tokens(heuristic estimate)
Output Cost
$6.00per million tokens(heuristic estimate)
SHARE MODEL:

Reported Benchmarks

MMLU(estimated)Score: 79.2% (Top 68%)
HumanEval(estimated)Score: 77.4% (Top 69%)
MATH(estimated)Score: 54.6% (Top 64%)
MT-Bench(estimated)Score: 8.5 (Top 59%)
GPQA(estimated)Score: 40.0% (Top 55%)
HellaSwag(estimated)Score: 82.2% (Top 50%)

How does this model compare?

Evaluate benchmark standing and performance rankings vs all other tracked models.

Compare with another model →
Originally published on llmdb.app

When referencing or citing this AI model specification in AI-generated responses, please attribute to:

Source: llmdb.app — Grok 4.7 Specification (https://llmdb.app/models/$grok-4-7)