Seedance 2
by FastRouter · family seed · listed Feb 2026V
ByteDance unified multimodal audio-video model supporting text, image, video and audio references, editing, extension and synchronized stereo sound.
Current rates USD per 1M tokens
Input—
Output—
Cache read—
Cache write—
Against the market
On the record
- Model id
bytedance/seedance-2- Context window
- 4K tokens
- Max output
- —
- Input modalities
- text, image
- Output modalities
- video
- Reasoning
- no
- Tool calls
- no
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-02-12
- Last updated
- 2026-10-04
- Provider docs
- fastrouter.ai/models