Seedance 2.0 API
ByteDance's Seedance 2.0 makes multi-shot clips with steady characters, believable motion and native sound with lip-sync.
Prices are temporarily unavailable — refresh the page in a minute.
↑ Result aboveWhat Seedance 2.0 is good for
Seedance 2.0 is ByteDance's multimodal video model that takes text, images, video clips, and audio in one request. Instead of relying on the prompt alone, it borrows motion, camera paths, transitions, and pacing from your references and keeps characters stable across multiple shots, with dialogue and effects generated in sync. It fits music videos, ads with realistic people, action scenes, and storyboard-to-video work up to 4K.
- Short music-video style clips with rhythmic motion and sound
- Multi-shot stories that keep the same character from scene to scene
- Fast action scenes with believable weight, momentum, and timing
- Talking-character clips with lip-sync created together with the picture
Seedance 2.0 pricing
| Option | Price, USD | Video Blade tokens |
|---|---|---|
| 480p | tokens | |
| 720p | tokens | |
| 1080p | tokens | |
| 4K | tokens |
Prices are per second and live from our price list. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing.
Use Seedance 2.0 from your AI agent
- Create an account on Video Blade and pick a plan — from .
- Copy the agent link from your dashboard into Claude Code, Codex or Cursor.
- Say the phrase below — the agent shows the price, runs Seedance 2.0 and saves the result.
Make an 8-second 9:16 720p clip with Seedance 2.0: a dancer in white sneakers crosses a city rooftop at sunset, the camera tracking every step, music with a steady beat.
This request ≈ · 720p · 8 s
Seedance 2.0 FAQ
How much does Seedance 2.0 cost?
8-second clip from · per second. Prices are live from our price list, and you see the exact price before anything runs.
How does Seedance 2.0 use reference videos and audio?
Upload a clip and Seedance 2.0 can follow its blocking, camera path, transitions, and editing rhythm in a new scene, so you show the move instead of describing it. A music track can set the pacing, with motion and cuts landing on the beat. Images lock in how characters and settings look.
Does Seedance 2.0 generate sound and lip-sync?
Yes. Seedance 2.0 creates audio together with the video, so dialogue, sound effects, and rhythm line up with what happens on screen. Speech is matched to lip movement, which makes it practical for talking characters, ads with spoken lines, and beat-matched edits without a separate sound pass.
How do I use Seedance 2.0 from my AI agent?
Create a Video Blade account, paste the agent link from your dashboard into Claude Code, Codex or Cursor, and ask: “Make an 8-second 9:16 720p clip with Seedance 2.0: a dancer in white sneakers crosses a city rooftop at sunset, the camera tracking every step, music with a steady beat.” The agent runs Seedance 2.0 (model id bytedance-seedance-2), shows the price before it starts and saves the result to your dashboard.
How is Seedance 2.0 billed?
By the second of video: the rate depends on the option you pick (mode, resolution, sound), and a clip costs the rate times its length. Tokens are held when a run starts and settled to what was actually used; a failed run costs nothing. Current prices are shown on this page.
What settings does Seedance 2.0 support?
Prompt: up to 20,000 characters. Resolution: 480p, 720p, 1080p or 4K. Aspect ratio: 1:1, 4:3, 3:4, 16:9, 9:16, 21:9 or adaptive.
Seedance 2.0 in the Video Blade API
bytedance-seedance-2Your agent sends this model id with the order; the result lands in the project, and every request is in your generation log with its price.
Through Video Blade a clip is ordered from a prompt with an optional start frame (and an end frame where the model takes one), in the lengths and resolutions the model offers.
POST /api/v1/projects/{id}/video-sessions/{item_id}/generate
{"prompt": "…", "model": "bytedance-seedance-2", "duration": …, "start_url": "https://…"}
Similar models
Seedance 2.5
Text to videoImage to video 8-second clip from · per second
Wan 3.0 Video
Text to videoImage to video 8-second clip from · per second
Wan 3.0 Video Prime
Text to videoImage to video 8-second clip from · per second