Qwen3 VL 235B A22B Instruct
Qwen🇨🇳
qwen/qwen3-vl-235b-a22b-instructQwen3 VL 235B-A22B Instruct is Alibaba's large-scale multimodal MoE model, combining Qwen3's language capability with vision understanding for image, document, and video tasks. It suits demanding multimodal applications needing near-flagship quality.
Cost rate
0.4x
Context
262K
Released
Sep 23, 2025
Input
TextImage
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Image understanding
#77 · top 48%
Business, Management, & Finance
#102 · top 25%
Legal & Government
#120 · top 31%
Life, Physical, & Social Science
#121 · top 29%
Performance
Median latency and throughput measured across recent requests.
Throughput53 tok/s
Latency