How to call the Seedance 2.0 video generation API

To call the Seedance 2.0 video generation API on RelayDance, set your OpenAI SDK base_url to https://relaydance.com/v1, add an Authorization: Bearer YOUR_API_KEY header, then POST to /v1/video/generations with model, prompt and seconds. Poll /v1/video/generations/{task_id} until the status is succeeded, or use a webhook. Pricing starts at about $0.190 per second for 720p output (source relaydance.com/models).

Configure the OpenAI-compatible endpoint

Point your existing OpenAI client at RelayDance by changing one value: the base URL. 据 relaydance.com/docs 官方文档，「Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK」, so no rewrite of your client code is required. Create an API key at https://relaydance.com/console and pass it as Authorization: Bearer YOUR_API_KEY. The base URL https://relaydance.com/v1 covers both video and image routes. This design gives direct OpenAI-compatible access to Seedance with no BytePlus enterprise account or KYC required. See the full reference at relaydance.com/docs.

Submit and poll a video task

Send a POST request to /v1/video/generations with your model, prompt and clip length, then poll for the result. Include seconds (clips can run up to 15 seconds) and optional metadata fields: ratio, resolution, generate_audio, callback_url and content[]. Reference media go in metadata.content[] and are cited in the prompt as @image1 to @imageN, with up to 9 reference images, 3 reference videos and 3 audio tracks per request. After submission, call GET /v1/video/generations/{task_id} until the status is succeeded or failed. On success, the response contains the video URL. For webhook mode, set metadata.callback_url and the final state is POSTed to your server.

Seedance 2.0 pricing and billing

Seedance 2.0 is billed pay-as-you-go per generated video, with rates that vary by resolution. According to relaydance.com/docs, 「Failed or errored requests are never billed」, so retries carry no charge for errored calls. Live per-model rates are published at relaydance.com/models.

Steps to run your first request

Follow these numbered steps to generate a Seedance 2.0 clip end to end.

1. Create an API key at https://relaydance.com/console.
2. Set base_url to https://relaydance.com/v1 in your OpenAI SDK.
3. Add the header Authorization: Bearer YOUR_API_KEY.
4. POST to /v1/video/generations with model, prompt and seconds (optionally add ratio, resolution and generate_audio in metadata).
5. Poll GET /v1/video/generations/{task_id} until status is succeeded, or set metadata.callback_url for a webhook.
6. Read the video url from the succeeded response.

FAQ

Do I pay for failed requests? No. Billing is pay-as-you-go per generated video, and failed or errored requests are never billed.

What payment methods are supported? USDT and Stripe card payments are accepted.

How many reference files can I attach? Up to 9 reference images, 3 reference videos and 3 audio tracks per request, placed in metadata.content[] and cited as @image1 to @imageN.