Grok 4.7 is now live in Command Code. 40% for the next 7 days. $35 credits (3.5x usage) in GOAT. Available on GOAT, Pro, Max, and via API. 🐐
Grok 4.7 at a glance
Coding and knowledge work, built for multi-hour tasks.
| Spec | Grok 4.7 |
|---|---|
| Model ID | xai/grok-4.7 |
| Context window | 500K tokens |
| Released | September 21, 2026 |
| Intelligence Index | 46.4 |
| Input | $1.20 per 1M tokens |
| Output | $3.60 per 1M tokens |
| Cache read | $0.30 per 1M tokens |
| Effective input in an agent loop | $0.57 per 1M tokens |
| Plans | GOAT and above |
Specs, pricing and plans are from the Grok 4.7 model page as of September 28, 2026, including any deal running that day, so they can differ from the launch pricing above. Intelligence and Coding Index scores are from Artificial Analysis.
Use Grok 4.7
1cmd --model xai/grok-4.7Or type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on Grok 4.7
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0067 |
| Review a 500-line PR | 60K · 4K | $0.05 |
| Fix a bug (agent loop) | 180K · 12K | $0.14 |
| Refactor a module | 320K · 20K | $0.25 |
| Full-repo agent run | 900K · 45K | $0.61 |
Try Command Code
The best coding agent for open models, in your terminal or on your desktop.
1npm i -g command-codeDesktop App · Docs · X · Discord
