China72B parametersImage + video128K context

Explore Qwen2.5-VL-72B-Instruct

Analyze images and video with Qwen's large vision-language model for documents, charts, localization, visual reasoning, and long-form video understanding.

Model

Qwen/Qwen2.5-VL-72B-Instruct

Input

Configure your request

System message Optional

Question or instruction

Images Optional

Upload one or more images.

Video Optional

Optional video input.

Parameters

Generation settings

Stream response Sample output

Temperature

Top P

Top K

Maximum output tokens

Minimum pixels per image

Maximum pixels per image

Video FPS

Seed

Stop sequences

Explore Qwen2.5-VL-72B-Instruct

Configure your request

Response