← Blog
ANNOUNCEMENT

Qwen 3.8 Omni Flash is live in Command Code

Qwen 3.8 Omni Flash is now live in Command Code. Available across all plans and API.

Team Command Code
2 min read
Sep 18, 2026

Qwen 3.8 Omni Flash is now live in Command Code. Available across all plans and API.

Qwen 3.8 Omni Flash at a glance

Omni-modal understanding & multimedia agentic work.

SpecQwen 3.8 Omni Flash
Model IDqwen/qwen3.8-omni-flash
Context window1M tokens
ReleasedSeptember 17, 2026
Input$0.15 per 1M tokens
Output$0.47 per 1M tokens
Cache read$0.02 per 1M tokens
Effective input in an agent loop$0.06 per 1M tokens
PlansGo and above

Specs, pricing and plans are from the Qwen 3.8 Omni 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 3.8 Omni Flash

1cmd --model qwen/qwen3.8-omni-flash

Or type /model in a session and pick it. You can switch mid-session without losing context.

What real work costs on Qwen 3.8 Omni Flash

TaskTokens (in · out)Cost
Quick lookup / one-liner8K · 1K$0.0007
Review a 500-line PR60K · 4K$0.0053
Fix a bug (agent loop)180K · 12K$0.01
Refactor a module320K · 20K$0.03
Full-repo agent run900K · 45K$0.06

Try Command Code

The best coding agent for open models, in your terminal or on your desktop.

1npm i -g command-code

Desktop App · Docs · X · Discord

Share this article