Agent may make mistakes. Verify all outputs.
Built with a unified multimodal audio-video joint generation architecture, Seedance 2.0 supports four input modalities: text, image, audio, and video. Compared with Version 1.5, Seedance 2.0 delivers a substantial leap in generation quality. It achieves a higher usability rate for complex interaction and motion scenes, with significant improvements in physical accuracy, visual realism, and controllability, making it well-suited for high-quality creation scenarios.
import { experimental_generateVideo as generateVideo } from 'ai';
const result = await generateVideo({ model: 'bytedance/seedance-2.0', prompt: 'A drone shot of a coastal cliff with crashing waves and a lighthouse in the distance at golden hour.'});Try out Seedance 2.0 by ByteDance. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Model |
|---|
| — | — |  | 04/14/2026 | ||||||||||
| — | — | | 01/28/2026 | ||||||||||
| — | — | | 12/16/2025 | ||||||||||
| — | — | | 11/28/2025 | ||||||||||
| — | — | | 10/31/2025 | ||||||||||
| 256K | 1.2s | 117tps | $0.25/M | $2.00/M | Read: $0.05/M Write: — | — | — | | 09/01/2025 | ||||
| 256K | 3.2s | 162tps | $0.25/M | $2.00/M | Read: $0.05/M Write: — | — | — | | 09/01/2025 | ||||
| — | — | | 08/28/2025 | ||||||||||
| — | — | | 06/11/2025 | ||||||||||
| — | — | | 06/01/2025 | ||||||||||
| — | — | | 06/01/2025 |