Video came out shorter than requested: Seedance duration limits and the 15 second cap
If your Seedance video came out shorter than requested, the cause is the per request duration limit: RelayDance supports clips up to 15 seconds per generation. When you submit a value in the seconds field of your video task, the output is bound by that 15 second cap. Requesting a longer duration will not extend a single clip beyond 15 seconds, so plan multi part sequences as separate requests. See the current rules at relaydance.com/models.
Why the video is shorter than requested
The output length is capped because RelayDance limits each video generation to clips up to 15 seconds. When you set the seconds parameter in a POST /v1/video/generations call, the returned clip cannot exceed 15 seconds regardless of a higher requested value. This is a per request boundary, not a per account one, so each new call resets to the same 15 second ceiling. To build longer content, submit multiple requests and join the resulting clips yourself. According to the official relaydance.com/docs, 「Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK」, so no client changes are needed to adjust the seconds value on retry.
How to fix a short clip step by step
You can address a shorter than expected clip by verifying your parameters and re submitting.
- Confirm the
secondsvalue in yourPOST /v1/video/generationsbody is 15 or lower, since clips run up to 15 seconds. - Poll
GET /v1/video/generations/{task_id}until status is succeeded or failed. - For content longer than 15 seconds, split it into separate requests, each up to 15 seconds.
- Use
metadata.content[]reference media (up to 9 reference images, 3 reference videos and 3 audio tracks) cited as @image1 to @imageN to keep continuity across clips. - Retry safely: 「Failed or errored requests are never billed」, per the official relaydance.com docs.
Duration limits and reference media per request
The limits are fixed per request, so knowing them helps you plan clip counts and reference assets.
| Limit | Value per request |
|---|---|
| Clip length | Up to 15 seconds |
| Reference images | Up to 9 |
| Reference videos | Up to 3 |
| Audio tracks | Up to 3 |
Reference media go in metadata.content[] and are cited in the prompt as @image1 to @imageN. Because billing is pay-as-you-go per generated video, a re run at a corrected duration is charged only when it succeeds.
What per second pricing means for clip length
Duration affects cost because Seedance 2.0 is billed per second. At 720p, Seedance 2.0 is about $0.190 / second, and at 1080p it is about $0.470 / second, so a full 15 second clip scales linearly with those rates. Seedance Fast is about $0.152 / second. Native 4K is priced differently, at about $4.90 per 5-second clip. Live per model rates are published at relaydance.com/models, and the OpenAI-compatible interface is documented at relaydance.com/docs. Set your seconds value with these rates in mind to control spend on each clip.
FAQ
Can a single Seedance clip be longer than 15 seconds? No. Clips run up to 15 seconds per request. For longer content, submit multiple requests and combine the clips.
Am I charged if the generation fails after I change the duration? No. 「Failed or errored requests are never billed」, according to the official relaydance.com docs.
How much does a 15 second clip cost at 1080p? Seedance 2.0 at 1080p is about $0.470 / second, billed pay-as-you-go per generated video. Check current rates at relaydance.com/models.
According to the official relaydance.com docs: "Failed or errored requests are never billed"
According to the official relaydance.com/docs docs: "Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK"
Key facts and figures
| Item | Value | Source |
|---|---|---|
| Seedance 2.0 720p price | about $0.190 / second | relaydance.com/models |
| Seedance 2.0 1080p price | about $0.470 / second | relaydance.com/models |
| Seedance Fast price | about $0.152 / second | relaydance.com/models |
| Seedance native 4K price | about $4.90 per 5-second clip | relaydance.com/models |
| gpt-image-2 image billing | image output is free, only input is billed; image-to-image from about CNY 0.035; 4K and 1K output cost the same | relaydance.com/models |
| API protocol | OpenAI-compatible; set base_url to https://relaydance.com/v1 | relaydance.com/docs |
| Failed requests | failed or errored requests are never billed | relaydance.com/docs |
Data verified 2026-06-29; live prices are on the official /models page.