LANGUAGE & CODING / xAI / SpaceXAI

Grok 4.7

Coding and configurable reasoning with agent tool support.

Checked 2026-10-05CodingAgents & toolsReasoning

PRICE / USD

$2

Per 1 million output tokens · input billed separately

Input / 1M tokens: $2
Output / 1M tokens: $6
Cached input / 1M tokens: Not verified
Cache write / 1M tokens: Not verified

Grok API · listed token rates

Web and X search require tools and incur additional charges. Cached rates were not verified for this entry.

Grok models ↗

SPEED & CAPABILITIES

Not benchmarked

No speed classification verified for this version and serving tier. This does not mean it is slow.

Model score: 46
Our own output-speed measurement: Not measured
Context window: 500,000
API model ID: grok-4.7

Artificial Analysis tested Grok 4.7 · xhigh. This mostly English, text-based index is not a guarantee of performance on your workload. Artificial Analysis · Grok 4.7 · xhigh ↗

Realtime knowledge requires search tools; it is not provided by the base model alone.

Suggested starting role: complex planning. Configurable reasoning and agent tools make Grok a candidate for multi-step analysis. Live web or X information requires separately billed search tools. This is editorial guidance, not a benchmark score.

Prices are USD per million native tokens, with input and output billed separately. Extra reasoning tokens, retries, tool calls, cache writes, storage, and taxes can change the bill. Use-case tags reflect our reading of official capabilities, not measured rankings.

Sources & methodology

Grok models ↗ Checked 2026-10-05

Artificial Analysis · Grok 4.7 · xhigh ↗ Checked 2026-10-05

Artificial Analysis · Intelligence Index methodology v4.3.2 ↗ Checked 2026-10-05

Open comparison →