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...
Rank
#118
Up 27% week over week
Tokens
17.7B
2026-08-14
Requests
5.1M
5,142,609
Tool calls
-
Input / M
$0.26
Output / M
$1.04
Cache / M
Free
Context
262K
262,144 tokens