Skip to content

Seedance 2.5

Seedance 2.5 is a next-generation audio-video joint generation model, built for 30-second storytelling with precise reference control and powerful editing capabilities. Your use is subject to ByteDance's Terms & Privacy Policies.

Video Gen

Use with AI Gateway View docs

import { experimental_generateVideo as generateVideo } from 'ai';

const result = await generateVideo({
  model: 'bytedance/seedance-2.5',
  prompt: 'A serene mountain lake at sunrise.'
});

Overview API Providers Similar

Copy link to headingMore models by ByteDance

Model

Context	Latency	Throughput	Input	Output	Cache	Web Search	Capabilities	Providers	ZDR	No Training	Release Date

bytedance/seedance-2.0

$7/M+1 more

—

04/14/2026

bytedance/seedance-2.0-fast

$5.60/M+1 more

—

04/14/2026

bytedance/seedance-v1.0-pro-fast

$0.01/sec+2 more

—

10/24/2025

bytedance/seed-1.8

256K

1.1s

96tps

$0.25/M+1 more

$2/M+1 more

Read:

$0.05/M

Write:

—

—

09/01/2025

bytedance/seed-1.6

256K

1.1s

79tps

$0.25/M+1 more

$2/M+1 more

Read:

$0.05/M

Write:

—

—

09/01/2025

bytedance/seedance-v1.0-pro

$0.02/sec+2 more

—

06/11/2025