Seedance 2.0 / 2.5 Explained (2026): specs, list price, what it is good for, where to use it
ByteDance's video model, available via Volcengine Ark API and Dreamina; 2.5 shipped July 2026 as Pro/Lite/Turbo.
Specs
| Segment length | 4–15 s (2.0); longer on 2.5 |
| Resolution | 480p / 720p (2.0); higher on 2.5 |
| Audio | Native audio (generate_audio) |
| References | First/last frame, reference image/video/audio, multimodal |
| Intra-segment cuts | Executes multi-shot prompts within one generation |
| List price | Token-billed: 2.0 ≈ ¥28 per 1M tokens, 2.5 ≈ ¥42 (+50%) |
| Where to use | Volcengine Ark API, Dreamina, and platforms integrating it (SceneMixer, PixVerse, Runway, Luma) |
Seedance 2.0 / 2.5 vs other video models: seconds per generation
Good for / caveats
Good for
Vertical drama segments, Chinese prompts, multimodal references
Caveats
Raw API means you manage references and storyboards; Dreamina does no episode splitting
Available in
FAQ
How much does Seedance 2.0 / 2.5 cost?
Token-billed: 2.0 ≈ ¥28 per 1M tokens, 2.5 ≈ ¥42 (+50%)
How long can one Seedance 2.0 / 2.5 generation be?
4–15 s (2.0); longer on 2.5 · 480p / 720p (2.0); higher on 2.5
Is Seedance 2.0 / 2.5 good for AI short drama?
Good for: Vertical drama segments, Chinese prompts, multimodal references. Caveat: Raw API means you manage references and storyboards; Dreamina does no episode splitting.
How do I use Seedance 2.0 / 2.5 without coding?
Through platforms that expose it: Dreamina (Jimeng), SceneMixer, PixVerse, Runway, Luma Dream Machine, Morph Studio, invideo AI
Sources
Official pages opened while writing; current pricing and features are always as shown on the vendor site.
- https://www.volcengine.com/docs/82379 — Seedance 2.0 / 2.5