← All models Model directory

AI model

SpaceXAI: Grok 4.7

x-ai/grok-4.7

SpaceXAI: Grok 4.7 is a 500,000-token model served on Composite at $0.512 per million tokens in and $4.80 per million tokens out. Ranked #89 of 180 models by traffic on Composite over the last 30 days, taking 0.04% of tokens and 0.02% of requests (this model and its routing variants). Measured on Composite, 100.0% of its last 29 requests on Composite succeeded, the typical first token arrives in 22281 ms, output runs at about 375.6 tokens per second.

Try in Playground

Community rating

— No community ratings yet.

Sign in to rate this model. Ratings come from accounts that have run requests through Composite.

Specifications

Specifications and pricing as served by Composite
Model IDx-ai/grok-4.7
Providercv11
Context window500,000 tokens
Acceptstext, image, file
Returnstext
Input price$0.512 per million tokens
Output price$4.80 per million tokens
Prompt cachingSupported — cached input is 60% off the list rate on pay-as-you-go credits
Web search$0.0050 per result
ThinkingAlways on for this model
ModeratedNo
Cost on a monthly plan16 requests of the daily allowance per call
Plans that may spend on itPlus, Pro, Ultra, Enterprise
Routing endpoints8 (base plus 7 routing variants)

Traffic rank on Composite

#89 of 180

0.04% of tokens and 0.02% of requests over 30 days, including routing variants.

Success rate

100.0%

Across the last 29 requests Composite served for this model.

Time to first token

22281 ms

Median across the same sample.

Output speed

375.6 tok/s

Median generation rate after the first token.

Prompt cache hits

15.4%

Share of prompt tokens served from the provider's cache over 7 days.

Routing variants

The same model behind 7 alternative endpoints. Call the id directly to pin a route; the base id above picks for you.

RouteModel IDProviderPrice
Normal x-ai/grok-4.7-normal cv11 $0.512 per million tokens input · $4.80 per million tokens output
Normal + cheapThink x-ai/grok-4.7-normal:cheapThink cv11 $0.512 per million tokens input · $4.80 per million tokens output
Cheapest provider x-ai/grok-4.7:cheapest-provider xAI $0.512 per million tokens input · $4.80 per million tokens output
Cheapest provider + cheapThink x-ai/grok-4.7:cheapest-provider:cheapThink xAI $0.512 per million tokens input · $4.80 per million tokens output
cheapThink x-ai/grok-4.7:cheapThink cv11 $0.512 per million tokens input · $4.80 per million tokens output
Fast x-ai/grok-4.7:fast xAI $1.02 per million tokens input · $9.60 per million tokens output
Fast + cheapThink x-ai/grok-4.7:fast:cheapThink xAI $1.02 per million tokens input · $9.60 per million tokens output

Pricing

$0.512 per million tokens input · $4.80 per million tokens output

Input and output are charged at the provider’s list price.

On a monthly plan, one call costs 16 requests of that day's allowance. That needs the Plus or Pro or Ultra or Enterprise plan; credits pay for it on any plan.

Provider

cv11

Roleplay fit

Grok models lean toward a more direct, less filtered writing style than many alternatives.

Context behavior

With a 500,000-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.

Cost for regular use

It sits in the mid-range on price, a reasonable pick for regular roleplay use without going for the cheapest option available.

From the provider

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...

Supplied by cv11, not written by Composite.