← All models
Qwen · Multimodal
Qwen: Qwen3 VL 235B A22B Instruct
Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...
Open-weightIn: Text, ImageOut: Text
Input / M
$0.21 / M
Output / M
$1.90 / M
Cache read / M
$0.10 / M
Context
262K
Released
Sep 23, 2025