How to call the Seedance 2.0 video generation API

To call the Seedance 2.0 video generation API on RelayDance, point your existing OpenAI SDK at the base URL https://relaydance.com/v1, authenticate with Authorization: Bearer YOUR_API_KEY, then POST to /v1/video/generations with a model, prompt, and seconds. Poll /v1/video/generations/{task_id} until the status is succeeded or failed. Seedance 2.0 720p costs about $0.190 per second (see relaydance.com/models).

Set the base URL and authenticate

Switch to RelayDance by changing only the base URL in your OpenAI-compatible client. According to the official relaydance.com/docs,"set base_url to https://relaydance.com/v1 and keep your OpenAI SDK". Create an API key at the console (https://relaydance.com/console), then pass it as Authorization: Bearer YOUR_API_KEY on every request. The interface is OpenAI compatible, so you do not need a BytePlus enterprise account or KYC to reach Seedance. Payments are pay-as-you-go and accepted via USDT and Stripe card. See relaydance.com/docs for the full request schema, including video and image endpoints.

Submit and poll a video task

Create a task by sending a POST to /v1/video/generations with model, prompt, and seconds. Add optional fields under metadata: ratio, resolution, generate_audio, callback_url, and a content[] array for reference media. Reference media are cited in the prompt as @image1 to @imageN, with up to 9 reference images, 3 reference videos, and 3 audio tracks per request, and clips up to 15 seconds. Then poll GET /v1/video/generations/{task_id} until status is succeeded or failed; the result contains the video url. For webhook delivery, set metadata.callback_url and the final state is POSTed to your server.

Per-model pricing

Seedance billing is pay-as-you-go per generated video, charged by the second or by clip. According to the official relaydance.com/models,"failed or errored requests are never billed", so errored requests never count against your usage. Live rates are published at relaydance.com/models.

Steps to your first generation

Follow these steps to produce a Seedance video end to end.

1. Create an API key at https://relaydance.com/console.
2. Set your OpenAI SDK base_url to https://relaydance.com/v1.
3. POST to /v1/video/generations with model, prompt, and seconds.
4. Optionally add metadata: ratio, resolution, generate_audio, callback_url, and content[] reference media cited as @image1 to @imageN.
5. Poll GET /v1/video/generations/{task_id} until status is succeeded or failed, or use a callback_url webhook.
6. Read the video url from the result.

FAQ

Do I need a BytePlus account to use Seedance? No. RelayDance provides direct OpenAI-compatible access to Seedance with no BytePlus enterprise account or KYC required.

Am I charged when a request fails? No. According to the official relaydance.com/models,"failed or errored requests are never billed".

How many reference media can I attach? Up to 9 reference images, 3 reference videos, and 3 audio tracks per request, with clips up to 15 seconds.