qwen/qwen3-vl-235b-a22b-thinking
Qwen3-VL-235B-A22B Thinking is a multimodal model that unifies strong text generation with visual understanding across images and video. The Thinking model is optimized for multimodal reasoning in STEM and math....
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Alibaba | $0.260 | $2.60 | 131K | 99% |
| Novitabf16 | $0.980 | $3.95 | 131K | — |
Qwen3 VL 235B A22B Thinking costs $0.260 per million input tokens and $2.60 per million output tokens via OpenRouter, making it 119th cheapest of 298 paid models.
Qwen3 VL 235B A22B Thinking scores 27.6 on the Artificial Analysis Intelligence Index, ranking 87th of 178 benchmarked models, with a GPQA Diamond score of 77%.
Qwen3 VL 235B A22B Thinking generates around 44 tokens per second with 1.3s time-to-first-token (p50), the 189th fastest tracked model.
Qwen3 VL 235B A22B Thinking supports a 131K-token context window and can output up to 33K tokens. It accepts text, image input.