Text to video API quickstart with an OpenAI compatible endpoint

To start generating video through RelayDance, set your OpenAI SDK base_url to https://relaydance.com/v1, add an Authorization Bearer key, then POST to /v1/video/generations with a model, prompt, and seconds. Poll /v1/video/generations/{task_id} until status is succeeded or failed, or use a webhook. Billing is pay-as-you-go: Seedance 2.0 720p costs about $0.190 per second, and failed requests are never billed.

How do I connect an OpenAI-compatible client

You connect by pointing an existing OpenAI SDK at the RelayDance base URL and supplying an API key. According to the official relaydance.com/docs, 「Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK」, so no separate client library is required. Authentication uses the header Authorization: Bearer YOUR_API_KEY, and keys are created at the console (https://relaydance.com/console). Because the endpoint is OpenAI-compatible, you gain direct access to Seedance without a BytePlus enterprise account or KYC. Payments are supported through USDT and Stripe card, and current per-model rates are published at https://relaydance.com/models. See the full reference at https://relaydance.com/docs.

What are the steps to submit a video task

You submit a task with a single POST request, then poll or wait for a webhook to receive the video URL.

1. Set base_url to https://relaydance.com/v1 and add your Bearer key.
2. POST to /v1/video/generations with model, prompt, seconds, and metadata (ratio, resolution, generate_audio, callback_url).
3. Add reference media in metadata.content[] and cite them in the prompt as @image1 to @imageN.
4. Poll GET /v1/video/generations/{task_id} until status is succeeded or failed, or set metadata.callback_url for webhook delivery.
5. Read the result, which contains the video url.

Each request accepts up to 9 reference images, 3 reference videos, and 3 audio tracks, with clips up to 15 seconds.

How much does video generation cost

Video generation is priced pay-as-you-go per generated video, with rates that vary by model and resolution. According to the official relaydance.com/models docs, Seedance 2.0 costs about $0.190 per second at 720p and about $0.470 per second at 1080p, while Seedance Fast costs about $0.152 per second. Seedance native 4K is priced at about $4.90 per 5-second clip. For images, gpt-image-2 output is free and only input is billed, image-to-image starts from about CNY 0.035, and 4K and 1K output cost the same. As stated in the relaydance.com docs, 「Failed or errored requests are never billed」.

Which models and reference inputs are available

RelayDance provides several video and image model families through one endpoint. Available models include ByteDance Seedance 2.0 and Seedance 1.5 Pro, HappyHorse video models, and Grok Imagine video and image models, plus Grok text models. Reference media are placed in metadata.content[] and cited in the prompt using tags @image1 to @imageN. Per request, you can include up to 9 reference images, 3 reference videos, and 3 audio tracks, and generate clips up to 15 seconds. Images are created through POST /v1/images/generations. Live per-model rates are listed at https://relaydance.com/models, and the request reference is at https://relaydance.com/docs.

FAQ

Do I pay for failed requests?

No. According to the relaydance.com docs, failed or errored requests are never billed.

What is the base URL for the API?

The base URL is https://relaydance.com/v1, used with your existing OpenAI SDK and a Bearer key.

How do I receive results without polling?

Set metadata.callback_url to enable webhook mode, and the final state is POSTed to your server with the video url.