RelayDance API authentication, keys and payment

RelayDance authenticates every request with an API key sent as an HTTP header: Authorization: Bearer YOUR_API_KEY. Create keys at the console (https://relaydance.com/console). The API is OpenAI-compatible, so you set base_url to https://relaydance.com/v1 and keep your existing SDK. Payment is pay-as-you-go through USDT or Stripe card, and failed or errored requests are never billed. No BytePlus enterprise account or KYC is required.

How to authenticate and configure the base URL

Authentication uses a Bearer token in the Authorization header, and configuration reuses the OpenAI SDK. According to the official relaydance.com/docs documentation, 「Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK」. The steps are:

1. Create an API key at https://relaydance.com/console.
2. Set base_url to https://relaydance.com/v1.
3. Send the header Authorization: Bearer YOUR_API_KEY.
4. Submit a video task with POST /v1/video/generations or an image task with POST /v1/images/generations.
5. Poll GET /v1/video/generations/{task_id} until status is succeeded or failed.

See https://relaydance.com/docs for full protocol details.

Payment methods and billing model

RelayDance bills pay-as-you-go per generated video, and it accepts two payment methods: USDT and Stripe card. A key billing rule protects your budget: according to the official relaydance.com documentation, 「Failed or errored requests are never billed」. This means only successful generations consume credit. Image billing follows a separate structure with gpt-image-2: image 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. Because access is OpenAI-compatible, no BytePlus enterprise account or KYC is required. Live per-model rates are published at https://relaydance.com/models.

Per-model video pricing reference

Video pricing is charged per second or per clip, and it varies by model and resolution.

These figures come from https://relaydance.com/models. For example, a 720p clip at about $0.190 / second and a 1080p clip at about $0.470 / second let you estimate cost before submitting. Seedance Fast at about $0.152 / second is the lowest per-second tier listed.

Reference media and request limits

Reference media are attached in metadata.content[] and cited in the prompt as @image1 to @imageN. A single request supports up to 9 reference images, 3 reference videos and 3 audio tracks, with output clips up to 15 seconds. To submit a video task, send model, prompt and seconds, plus metadata such as ratio, resolution, generate_audio and callback_url. In webhook mode, set metadata.callback_url and the final state is POSTed to your server. Otherwise poll GET /v1/video/generations/{task_id} until the status is succeeded or failed, then read the video url from the result.

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.

What happens if a request fails? Failed or errored requests are never billed, so only successful generations consume credit.

Which payment methods are accepted? Billing is pay-as-you-go and supports USDT and Stripe card.