Qwen 3.8 Max 0902 is now live in Command Code.
It's an upgraded Qwen 3.8 Max:
- 2.4T params
- 1M context
- Post-trained on coding & cowork
Available on GOAT, Pro, Max and API
Qwen 3.8 Max 0902 at a glance
Upgraded Qwen 3.8 Max: stronger coding & agentic tool use.
| Spec | Qwen 3.8 Max 0902 |
|---|---|
| Model ID | qwen/qwen3.8-max-0902 |
| Context window | 1M tokens |
| Released | September 2, 2026 |
| Intelligence Index | 45.4 |
| Coding Index | 76.2 |
| Input | $2 per 1M tokens |
| Output | $6 per 1M tokens |
| Cache read | $0.25 per 1M tokens |
| Effective input in an agent loop | $0.78 per 1M tokens |
| Plans | Go and above |
Specs, pricing and plans are from the Qwen 3.8 Max 0902 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 Max 0902
1cmd --model qwen/qwen3.8-max-0902Or type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on Qwen 3.8 Max 0902
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0094 |
| Review a 500-line PR | 60K · 4K | $0.07 |
| Fix a bug (agent loop) | 180K · 12K | $0.20 |
| Refactor a module | 320K · 20K | $0.36 |
| Full-repo agent run | 900K · 45K | $0.84 |
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
