Built for coding, agentic tasks, and knowledge work.
- Available on all plans (Go, Pro, Max)
- $2/M input, $6/M output tokens
How to use?
- $ cmd update or $ npm i -g command-code@latest
- Switch with /model
Grok 4.5 at a glance
Smartest model for coding, agentic tasks, knowledge work.
| Spec | Grok 4.5 |
|---|---|
| Model ID | xai/grok-4.5 |
| Context window | 500K tokens |
| Released | July 8, 2026 |
| Intelligence Index | 38.8 |
| Coding Index | 72.4 |
| Input | $2 per 1M tokens |
| Output | $6 per 1M tokens |
| Cache read | $0.50 per 1M tokens |
| Effective input in an agent loop | $0.95 per 1M tokens |
| Plans | Go and above |
Specs, pricing and plans are from the Grok 4.5 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 4.5
1cmd --model xai/grok-4.5Or type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on Grok 4.5
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.01 |
| Review a 500-line PR | 60K · 4K | $0.08 |
| Fix a bug (agent loop) | 180K · 12K | $0.23 |
| Refactor a module | 320K · 20K | $0.41 |
| Full-repo agent run | 900K · 45K | $1.02 |
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
