Claude Sonnet 5.5 is now live in Command Code. It runs 30% faster and costs 30% less, and it beats Opus 5.5 on Terminal-Bench 4.0. It's available on the GOAT, Pro and Max plans and through the API.
Claude Sonnet 5.5 at a glance
Best combo of speed and intelligence.
| Spec | Claude Sonnet 5.5 |
|---|---|
| Model ID | anthropic/claude-sonnet-5-5 |
| Context window | 1M tokens |
| Released | September 28, 2026 |
| Intelligence Index | 56 |
| Input | $2 per 1M tokens |
| Output | $10 per 1M tokens |
| Cache read | $0.20 per 1M tokens |
| Effective input in an agent loop | $0.74 per 1M tokens |
| Plans | GOAT and above |
Specs, pricing and plans are from the Claude Sonnet 5.5 model page as of October 6, 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 Claude Sonnet 5.5
1cmd --model anthropic/claude-sonnet-5-5Or type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on Claude Sonnet 5.5
| 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 | $0.24 |
| Refactor a module | 320K · 20K | $0.43 |
| Full-repo agent run | 900K · 45K | $0.99 |
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
