Qwen 3.7 Flash is now live in Command Code.
- 1M context window
- Available on all plans (Go, Pro, Max, Team).
Pricing is tiered. For ≤ 32K it's as low as:
- Input $0.03 Output $0.13
- Cache r/w $0.006/$0.038
Qwen 3.7 Flash at a glance
Fast low-cost agentic coding & reasoning.
| Spec | Qwen 3.7 Flash |
|---|---|
| Model ID | qwen/qwen3.7-flash |
| Context window | 1M tokens |
| Released | July 28, 2026 |
| Input | $0.03 per 1M tokens |
| Output | $0.13 per 1M tokens |
| Cache read | $0.006 per 1M tokens |
| Effective input in an agent loop | $0.01 per 1M tokens |
| Plans | Go and above |
Specs, pricing and plans are from the Qwen 3.7 Flash 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 3.7 Flash
1cmd --model qwen/qwen3.7-flashOr type /model in a session and pick it. You can switch mid-session without losing context.
What real work costs on Qwen 3.7 Flash
| Task | Tokens (in · out) | Cost |
|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0002 |
| Review a 500-line PR | 60K · 4K | $0.0013 |
| Fix a bug (agent loop) | 180K · 12K | $0.0037 |
| Refactor a module | 320K · 20K | $0.0067 |
| Full-repo agent run | 900K · 45K | $0.02 |
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
