Models

← All models

Doubao 1.5 Thinking Vision Pro 250428

ByteDance Seed · 2025-05-13

Doubao 1.5 Thinking Vision Pro 250428 is Volcano Engine's hosted doubao-1-5-thinking-vision-pro-250428 snapshot of ByteDance Seed's Seed1.5-VL vision-language model. It accepts text, image, and video input and returns text, with capabilities spanning visual and video understanding, multimodal reasoning, document understanding, and GUI control. Deep thinking is enabled by default in the API but can be disabled per request.

Benchmark scores