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...
The figures
- Made by
- Qwen
- Model ID
- qwen/qwen3-vl-235b-a22b-instruct
- Input
- $0.21 per million tokens
- Output
- $1.9 per million tokens
- Context window
- 262K tokens
- Longest answer
- 33K tokens
- Takes in
- text, image
- Gives back
- text
- Reasoning
- No
- Tool calling
- Yes
- Reads images
- Yes
- Open weights
- Yes
- Released
- 23 Sept 2025
Read on 3 Oct 2026.