Qwen 3.8 27B is now live in Command Code. Beats Opus 4.6 Max, GPT 5.6 Luna Max on the Artificial Analysis Intelligence Index.
Best for coding and long agent tasks. Multimodal with reasoning toggled on/off. Available on all plans & API 🐐
Qwen 3.8 27B at a glance
Compact vision-language coding & agentic work.
| Spec | Qwen 3.8 27B |
|---|---|
| Model ID | qwen/qwen3.8-27b |
| Context window | 262K tokens |
| Released | August 14, 2026 |
| Intelligence Index | 33.7 |
| Coding Index | 68.1 |
| Input | $0.40 per 1M tokens |
| Output | $3 per 1M tokens |
| Cache read | $0.04 per 1M tokens |
| Effective input in an agent loop | $0.15 per 1M tokens |
| Plans | Go and above |
Specs, pricing and plans are from the Qwen 3.8 27B 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 Qwen 3.8 27B
1cmd --model qwen/qwen3.8-27bOr type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on Qwen 3.8 27B
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0036 |
| Review a 500-line PR | 60K · 4K | $0.02 |
| Fix a bug (agent loop) | 180K · 12K | $0.06 |
| Refactor a module | 320K · 20K | $0.11 |
| Full-repo agent run | 900K · 45K | $0.24 |
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
