← Blog
ANNOUNCEMENT

Qwen 3.8 27B is live in Command Code

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.

Team Command Code
2 min read
Aug 19, 2026

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.

SpecQwen 3.8 27B
Model IDqwen/qwen3.8-27b
Context window262K tokens
ReleasedAugust 14, 2026
Intelligence Index33.7
Coding Index68.1
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
PlansGo 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/qwen3.8-27b

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 27B

TaskTokens (in · out)Cost
Quick lookup / one-liner8K · 1K$0.0036
Review a 500-line PR60K · 4K$0.02
Fix a bug (agent loop)180K · 12K$0.06
Refactor a module320K · 20K$0.11
Full-repo agent run900K · 45K$0.24

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