Qwen 3.8 Max is now live in Command Code Go. ... and it's going open weight!! most importantly, next week open-weights of Qwen3.8-Max and Qwen3.8-27B will be released!
- 2.4T params MoE flagship
- Input: $2 Output: $6
- Cache: $0.25 / M tokens
3.8 is 20% cheaper than 3.7
Qwen 3.8 Max at a glance
Autonomous long-horizon coding & professional work.
| Spec | Qwen 3.8 Max |
|---|---|
| Model ID | qwen/qwen3.8-max |
| Context window | 1M tokens |
| Released | August 3, 2026 |
| Intelligence Index | 40.2 |
| Coding Index | 71.8 |
| 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 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
1cmd --model qwen/qwen3.8-maxOr 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
| 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
