RelayDanceDocs / Help / FAQ
FAQ
Common questions about RelayDance.
#General
How does video generation work?
Asynchronously. POST /v1/video/generations returns a task id immediately. Poll GET /v1/video/generations/{task_id}, or set metadata.callback_url when submitting and we POST the final result to your webhook so you never poll.
How long can clips be?
Up to 15 seconds per request depending on model, at 480p to 1080p. Audio generation is supported on Seedance 2.0 models.
Can I use reference images?
Yes. Up to 9 reference images, 3 reference videos and 3 reference audio tracks per request via metadata.content[], referenced in the prompt as @image1 to @imageN.
What payment methods are accepted?
USDT and credit or debit cards via Stripe checkout.
Am I charged for failed generations?
No. Failed or errored tasks are never billed.
#API usage
How do I see which models my key can use?
Call GET /v1/models with your key, or browse the Models page. The per-key list returned by the API is the source of truth.
Are there rate limits?
Yes, standard rate limits apply per key. If you receive 429 Too Many Requests, slow down and retry with exponential back-off. Contact support@relaydance.com if your workload needs higher limits.
How do I get support?
Email support@relaydance.com. Include the request timestamp and, for async tasks, the task ID so we can trace it quickly.