Qwen3.8 27B
Dense 27B vision-language model for coding, agent tasks, and image and video understanding
Context
262,144
Max output
65,536
Input / 1M
$0.45
Output / 1M
$1.49
Providers
3
01Profile
Profile
Released
2026-08-14
Last updated
2026-09-03
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
Yes
Tool calling
Yes
Structured output
Yes
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 3 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
3+ recent events since 2026-08-14
2026-09-06Addedcerebrasoffering→ new
2026-08-26Addedneuralwattoffering→ new
2026-08-18Addedveniceoffering→ new