Qwen3 VL 235B A22B Instruct
Specifications
- Input
- Output
- Context window
- 131K tokens
- Released
- Sep 2025
Performance
- Speed
- 32 t/s
- TTFT
- 684 ms
- Latency
- —
- Intelligence
- —
Pricing
- Input
- €0.25 per 1M tokens
- Output
- €2.19 per 1M tokens
About this model
Qwen3 VL 235B A22B Instruct is Alibaba's vision-language MoE model with 235B total / 22B active parameters. Combines state-of-the-art text and vision understanding with excellent performance on multimodal reasoning tasks.
Technical specifications
- Capabilities
- Input modalities
- Output modalities
- Reasoning
- No
Knowledge horizon
Knowledge cutoff Sep 2025
Released Sep 2025
Today
Training to release 0 mo Since release 8 mo
See also
Add Model to Comparison
Search for a model to add