xAI · API model
Grok 4.7
Generally availableReleased Sep 21, 2026Proprietary
API id grok-4.7 prices checked
- Input
- $2.00/1M
- Output
- $6.00/1M
- Context
- 500Ktokens
- Max output
- —tokens
- Knowledge cutoff
- May 2026
- Typical request
- $0.005
Pricing
US dollars per 1 million tokens. A typical request (1,000 input + 500 output tokens) costs $0.005 at standard rates.
| Rate | Input | Cached input | Output |
|---|---|---|---|
| Standard | $2.00 | $0.50 | $6.00 |
| Long promptsPrompts over 200K tokens | $4.00 | $1.00 | $12.00 |
| BatchAsynchronous, results within 24 hours | $1.60 | — | $4.80 |
| PriorityPriority, 2x standard. Grok 4.7 Fast is a separate variant sold only through Cursor and Grok Build. | $4.00 | — | $12.00 |
Capabilities and limits
| Context window | 500K tokens |
|---|---|
| Max output | — tokens |
| Input | TextImagesFiles (PDF) |
| Output | Text |
| Reasoning | Adjustable effort |
| Tool use | Yes |
| Structured output (JSON) | Yes |
| Knowledge cutoff | May 2026 |
Lifecycle status
No deprecation or shutdown date announced on xAI's official deprecations page as of Oct 23, 2026.
Change history
Launches, price changes and retirements for Grok 4.7, newest first, each linked to the vendor's notice.
Benchmarks and speed
Not collected yet. Scores will come only from independent leaderboards, each shown with its source and test date.
Planned: GPQA Diamond, SWE-bench Verified, AIME 2025, LMArena Elo, output speed and time to first token.
Where these numbers come from
Every value is an observation with a source and a date. independent is a third-party catalog, vendor is the model maker's own page, derived is our calculation.
| Field | Value | Source | Observed |
|---|---|---|---|
| Standard price, input / output | $2.00 / $6.00 | vendorxAI docs | Nov 5, 2026 |
| Standard price, input / output | $2.00 / $6.00 | independentLiteLLM | Nov 5, 2026 |
| Standard price, input / output | $2.00 / $6.00 | independentOpenRouter | Nov 5, 2026 |
| Release date | 2026-09-21 | vendorxAI | Nov 5, 2026 |
| Context window | 500,000 | vendorxAI model docs | Nov 5, 2026 |
| Max output | xAI does not list it. LiteLLM 500,000; OpenRouter 450,000 | independentOpenRouter | Nov 5, 2026 |
| Knowledge cutoff | xAI says May 2026; LLM Stats says June 2026 | vendorxAI model docs | Nov 5, 2026 |
| Input types | Text and image on the vendor's model page; OpenRouter also lists file input | vendorxAI model docs | Nov 5, 2026 |
| Benchmarks at launch | Terminal-Bench 4.0 37.6%, CursorBench 4.0 46.3%, DeepSWE v1.1 71.0% (xAI's own figures) | vendorxAI launch post | Nov 5, 2026 |
| Typical request | $0.005 | derivedai-magazine calculation: 1,000 input + 500 output tokens | Nov 5, 2026 |