Qwen 3 VL 235B

Alibaba's Qwen 3 VL vision-language model

Qwen 3 VL 235B on Melius

  1. Reason over text

    Add Qwen 3 VL 235B to a text node and reason over text without leaving your canvas.

  2. Understand images and video alongside text

    Add Qwen 3 VL 235B to a text node and understand images and video alongside text without leaving your canvas.

Try out Qwen 3 VL 235B on Melius

Frequently asked questions

What is Qwen 3 VL 235B?

Qwen 3 VL 235B is Alibaba's large vision-language model, reasoning across text, images, and video.

How do I use Qwen 3 VL 235B on Melius?

Melius is a node-based canvas: add a text node, pick Qwen 3 VL 235B from the model picker, and connect it to whatever should feed it or follow it. You only pay for what you generate.

Explore other models