Seedance 2.5
Generally availableProprietary
Summary
Seedance 2.5 is a proprietary video generation model from ByteDance Seed, released on 31 Jul 2026. It accepts text and generates video.
ByteDance multimodal audio-video model with up to 30-second single-pass generation, multi-round extension, reference inputs and timestamp-level editing.
Last verified 21 Oct 2026. Every figure on this page links to its source.
Specifications
| Developer | ByteDance Seed |
|---|---|
| Release date | 31 Jul 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Proprietary (API only) [models.dev] |
| Input | Text [models.dev] |
| Output | Video [models.dev] |
| Reasoning mode | No [models.dev] |
| Tool calling | No [models.dev] |
Seedance 2.5 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| Vercel AI Gateway bytedance/seedance-2.5 | – | – | – | – | models.dev, 21 Oct 2026 |
Frequently asked questions
Is Seedance 2.5 open source?
No. Seedance 2.5 is a proprietary model; ByteDance Seed has not released its weights. It is available through APIs including Vercel AI Gateway.
When was Seedance 2.5 released?
ByteDance Seed released Seedance 2.5 on 31 Jul 2026, according to models.dev.
Change history
- Added to the directory
- Now listed on Vercel AI Gateway