Models/Grok 4.7 (Xhigh)

Grok 4.7 (Xhigh)Ready

grok-4-7

Serverless APILLMReasoningVisionPrompt cachingClosed

A competitive reasoning release with aggressive pricing for throughput-heavy products. It ranks #9 of the top 20 frontier models on the Artificial Analysis Intelligence Index with a score of 46.4. Released September 21, 2026.

500K

Context

—

Parameters

Intelligence rank · 46.4

Closed

Weights

View full spec

ReleasedSep 21, 2026

Knowledge cutoff—

Size classlarge

Input modalitiestext, image

Output modalitiestext

Median output speed93 tok/s

Median time to first token49.0s

Usage guide

1. Choose how you'd like to use Grok 4.7 (Xhigh)

☁️ Serverless

Use with pay-per-token pricing. Zero setup, no cold starts, automatic failover between upstream routes.

Usage tiers · Standard • Priority

Try it — sign in

curl https://tokenhub-staging.coality.io/v1/chat/completions \
  -H "Authorization: Bearer $TOKEN_HUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4-7",
    "messages": [{"role": "user", "content": "Explain vector databases in one paragraph"}]
  }'

Pricing

Bucket	Price	Notes
Input tokens	$2.50	per 1M tokens
Output tokens	$7.50	per 1M tokens
Cache read	$0.6250	cached input · 75% off
Cache write	—	per 1M tokens

Billed per token with micro-dollar precision · effective Oct 26, 2026 · default key limits 600 req/min · 200K tokens/min

Benchmarks

Humanity's Last Exam

43.1

SciCode

57.4

Terminal-Bench 4.0

25.8

Long Context Reasoning

76.7

Frontier Code

33.8

Scores from the Artificial Analysis evaluation suite (0–100 scale).

About this model

Closed model, with a 500K context window, native image input, visible reasoning traces, prompt caching at a 75% discount on cached input, 93 output tokens/s median serving speed and 49.0s to first token.