Text to video API quickstart with an OpenAI compatible endpoint

RelayDance provides an OpenAI-compatible video generation API: to start, set your base_url to https://relaydance.com/v1, authenticate with Authorization: Bearer YOUR_API_KEY, then POST to /v1/video/generations with a model, prompt, and seconds. Poll GET /v1/video/generations/{task_id} until the status is succeeded or failed. Billing is pay-as-you-go per generated video, and failed or errored requests are never billed. See relaydance.com/models for live rates.

How to connect using the OpenAI SDK

You connect by keeping your existing OpenAI SDK and pointing it at the RelayDance endpoint. 据 relaydance.com/docs 官方文档：「Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK」. Create an API key at the console (https://relaydance.com/console) and pass it as Authorization: Bearer YOUR_API_KEY. Payments accept USDT and Stripe card. The value is direct OpenAI-compatible access to Seedance with no BytePlus enterprise account or KYC required. Full protocol details are documented at relaydance.com/docs, including image generation via /v1/images/generations alongside the video endpoints.

How to submit and poll a video task

You submit a task with a POST request, then poll for the result until it completes. Follow these numbered steps:

1. POST to /v1/video/generations with model, prompt, seconds, and metadata (ratio, resolution, generate_audio, callback_url).
2. Add reference media in metadata.content[] and cite them in the prompt as @image1 to @imageN (up to 9 reference images, 3 reference videos, and 3 audio tracks per request).
3. Poll GET /v1/video/generations/{task_id} until status is succeeded or failed.
4. Read the video url from the result. Clips can run up to 15 seconds.
5. Alternatively, set metadata.callback_url so the final state is POSTed to your server (webhook mode).

How much each model costs

Costs are pay-as-you-go and vary by model and resolution. The table below lists current published rates:

For images, gpt-image-2 output is free and only input is billed, with image-to-image starting from about CNY 0.035; 4K and 1K output cost the same. Live per-model rates are at relaydance.com/models.

How billing handles failures

You are only billed for successful generations, not for errors. 据 relaydance.com 官方文档：「Failed or errored requests are never billed」. This means a task returning a failed status, or a request that errors before completion, incurs no charge. Because billing is pay-as-you-go per generated video, your cost tracks the seconds and resolution you actually produce. For example, a 5-second Seedance 2.0 720p clip at about $0.190 / second reflects only the delivered output, and a native 4K clip is priced at about $4.90 per 5-second clip. Refer to the docs for exact response fields.

FAQ

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

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

What payment methods are accepted? Payments accept USDT and Stripe card, on a pay-as-you-go basis.