← All models
Qwen · Video
Qwen: Qwen3.5 397B A17B
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. It delivers...
Open-weightIn: Text, Image, VideoOut: Text
Input / M
$0.45 / M
Output / M
$3.00 / M
Cache read / M
$0.22 / M
Context
262K
Released
Feb 16, 2026