Seed Diffusion Preview

code

An experimental diffusion language model specialized for code generation achieves an inference speed of 2,146 token/s.

Capabilities

Infrastructure
Streaming

Details

Model IDseed-diffusion-preview
Provider ByteDance Seed
Creator bytedance
Family—
License—
Statusactive
Typecode
Input modalitiestext
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window—
Max input—
Max output—
Reasoning tokens—
Knowledge cutoff—
Release date—
Sourceofficial

Endpoints

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

API

GET/v1/models/bytedance/seed-diffusion-preview