NezhaGateNezhaGate
Video ● Operational Service status →

Seedance 2.0 · Clip

⧉
seedance-2.0-clip
Model Type 2.02.0 Fast2.0 · Special

Seedance 2.0 at a special per-clip price: $1.00 a clip, and 5, 10 or 15 seconds all cost the same -- the same 15 seconds on the per-second seedance-2.0 (720P) is $2.25, so this is 56% cheaper, and 33% cheaper at 10 seconds. 720P output: landscape 16:9 at 5, 10 or 15 seconds, portrait 9:16 at 15 seconds; up to 9 reference images (they set the people, scene and style; name them @Image1... in the prompt), and photos of real people work as references. Native audio included. Asynchronous; failed jobs refunded in full.

Special pricePer-clip pricingReal-face references720P
Our test renders· 2026-10
5.7 minMedian render time per clip

Live Test · Playground

Try out Seedance 2.0 · Clip right here (available after login).

Input

0 / 5000 bytes
Allowed lengths: 720P 5/10/15s · portrait 9:16: 15 s only
Reference images0 / 9
Click to upload or drag files here jpg / png / webp / gif, up to 16 MB each or paste links
With multiple references, address them in the prompt as @Image1 / @Image2, e.g. "the character from @Image1 stands in the scene from @Image2". Without tokens the model decides on its own.
Real human faces work as reference images, no masking needed. Please make sure you have the right to use the likeness of anyone pictured.
Uploaded references are kept for 7 days.
Rendering usually takes 3-10 min; poll the job id rather than resubmitting. Billed per clip (5 / 10 / 15 s at one price), fully refunded on failure. Prompt limit 5000 bytes (about 1666 Chinese characters).

Output

video
Results will appear here after running.
🕑 Results are kept for 60 days and then deleted automatically, so download anything you want to keep.

About Seedance 2.0 · Clip

Seedance 2.0 · Clip is the special-price tier of ByteDance Seedance 2.0: billed per clip, $1.00 a clip, and 5, 10 and 15 seconds all cost the same. 720P output, landscape 16:9 at 5, 10 or 15 seconds or portrait 9:16 at 15 seconds, up to 9 reference images -- they set the people, wardrobe, scene and style, and you address them in order as @Image1, @Image2 in the prompt; photos of real people work as references. The clip carries a native soundtrack. Async job: POST /v1/videos/generations returns HTTP 202 and a job id immediately; poll GET /v1/videos/jobs/{id} until status=succeeded and read data[0].url -- an mp4 re-hosted by us and kept for 60 days.

Use cases

Real people on camera

Use photos of real people as references and the faces stay consistent through the clip -- good for talking heads, short dramas and brand ambassadors.

15 seconds is the bargain

Per-clip pricing makes 15 seconds cost the same as 5; when you need the whole story, just take 15.

Vertical short-form

15-second 9:16 straight out of the model, ready for short-video platforms.

Batch product videos

A fixed $1.00 per clip makes the cost obvious, so you can run dozens of product clips and keep the best.

How to choose

Pick it for 10- or 15-second clips, or when the material features real people: 15 seconds costs $1.00, 56% less than the per-second seedance-2.0 (720P $0.15/s). For a 5-second clip the per-second seedance-2.0 is cheaper ($0.75); for 480P / 1080P, more aspect ratios, reference video or reference audio, use seedance-2.0 too; for a 30-second clip use seedance-2.5-30s (special price, $1.50 a clip).

FAQ

How is the special price billed?
Per clip: $1.00 a clip, 5 / 10 / 15 seconds at one price. The hold placed at submit is one clip's price and the settle is the exact same number; failed, content-rejected or timed-out jobs are refunded in full.
Can I ask for 8 or 12 seconds?
No. This tier offers 5, 10 and 15 seconds, and portrait 9:16 is 15 seconds for now; any other value is refused at submit and nothing is charged. Use seedance-2.0 when you need to pick the length to the second.
Does it handle real faces?
Yes. Photos of real people work as reference images as they are -- no blurring or masking -- and the faces stay consistent in the clip. Make sure you have the right to use the likeness of anyone in the photos.
Does it take reference video, reference audio or a first frame?
No. This tier takes reference images only (up to 9); they set the people, scene and style and are not used as the first frame. Use seedance-2.0 for reference video or reference audio.
How long does it take?
About 3-10 minutes for a 15-second clip in our tests. Poll the async job rather than waiting synchronously.

Related Models

Explore other models you can integrate.

View all →