Seed1.5-VL

Name: Seed1.5-VL
Author: ByteDance Seed

A large vision-language multimodal model, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

Capabilities

Show unsupported (7)

Infrastructure

Streaming

Creatorbytedance

Family—

License—

Statusactive

Typechat

Input modalitiestext, image

Output modalitiestext

Open weight—

Parameters—

Architecture—

Context window—

Max input—

Max output—

Reasoning tokens—

Knowledge cutoff—

Release date—

Sourceofficial

Chat CompletionsPOST

Generate chat responses with messageshttps://console.volcengine.com/ark/v1/chat/completions

GET/v1/models/bytedance/seed1.5-vl

A large vision-language multimodal model, achieving state-of-the-art performance on 38 out of 60 public benchmarks.

Changes · 2 entries

seed1.5-vlcreateca7a400Nov 2, 2026, 03:02 AM

seed1.5-vlcreate08f0ffeMay 11, 2026, 08:27 AM