xAI Grok 4.7 API Pricing and Speed

• $2.00Input per 1M tokens, from xAI Published
• $6.00Output per 1M tokens, from xAI Published
• $0.50Cached input per 1M tokens, from xAI Published

OpenRouter sends a call without a pinned provider to one of these endpoints, and each endpoint has its own price. Prices are USD per 1M tokens, input / output.

Pinned min: $2.00 / $6.00 · Amazon Bedrock (amazon-bedrock/global)

Unpinned range: input $2.00–$4.00, output $6.00–$12.00 across 6 endpoints of 2 providers (listing shows $2.00 / $6.00).

Models with the widest provider price spread on OpenRouter

{"provider": {"order": ["amazon-bedrock/global"], "allow_fallbacks": false}}

With fallbacks turned off, OpenRouter does not move the call to another provider. A full endpoint tag pins that endpoint; the provider name alone covers all of its endpoints (OpenRouter provider routing).

• Calculated Extra input billed: about 1,224 tokens more than the typical count for the same short request (1,599 billed against 375 across the models we test).
• Hidden reasoning tokens are billed as output, at the output price, even though they are not part of the answer.
• Observed Billed by the provider: the cost xAI states in its own API response to our test request, next to our estimate from the published prices.
• Through OpenRouter, the request goes to the named provider; the price and speed can differ from the direct API.

How the test works and what each number means: methodology. The figures are also in our open data.

• Your own task: quality on it is not measured here. These are public test sets; a short trial on a few of your own examples is the check that fits your work.
• Other public leaderboards, without figures copied here: human preference votes on open-ended answers: Arena (LMArena) text leaderboard; long tasks in coding, data analysis and research: LiveBench.

What each signal covers and how our run is scored: methodology.