Multi reference image fusion for video generation

RelayDance supports multi reference image fusion through the metadata.content[] field on the video generation endpoint, where you attach reference media and cite each item in the prompt as @image1 to @imageN. A single request accepts up to 9 reference images, 3 reference videos, and 3 audio tracks, with clips up to 15 seconds. The API is OpenAI compatible (base URL https://relaydance.com/v1), and failed requests are never billed.

How to attach multiple reference images

Place every reference image in the metadata.content[] array and reference them in your prompt as @image1 to @imageN. A single POST to /v1/video/generations carries the model, prompt, seconds, and metadata (ratio, resolution, generate_audio, callback_url, and the content[] reference media). Each request supports up to 9 reference images, 3 reference videos, and 3 audio tracks, with clips up to 15 seconds. According to the official documentation, the interface is OpenAI compatible: "set base_url to https://relaydance.com/v1 and keep your OpenAI SDK"(According to the official relaydance.com/docs). See relaydance.com/docs for the request schema.

Submitting and polling a fusion task

Submit the fusion request, then poll until the task reports a final status. POST your payload to /v1/video/generations, then call GET /v1/video/generations/{task_id} until status is succeeded or failed; the result contains the video url. As an alternative, set metadata.callback_url to use webhook mode, and the final state is POSTed to your server.

1. Add up to 9 images, 3 videos, and 3 audio tracks to metadata.content[].
2. Cite each item in the prompt as @image1 to @imageN.
3. POST to /v1/video/generations with model, prompt, and seconds.
4. Poll GET /v1/video/generations/{task_id} until succeeded or failed.

Per-second pricing for Seedance video

Video generation is billed pay-as-you-go per generated second or per bar, with rates listed by model. Seedance 2.0 at 720p is priced at about $0.190 per second, and 1080p is about $0.470 per second. Seedance Fast is about $0.152 per second, and Seedance native 4K is about $4.90 per 5 second bar. Failed or errored requests are never charged: according to the official documentation, "failed or errored requests are never billed"(According to the official relaydance.com docs). Live per-model rates are published at relaydance.com/models.

Authentication and payment

Authenticate every request with a Bearer API key created in the console. Pass Authorization: Bearer YOUR_API_KEY and create keys at https://relaydance.com/console. The API is OpenAI compatible, so you keep the OpenAI SDK and change only the base URL to https://relaydance.com/v1. Payments are accepted through USDT and Stripe card, and billing is pay-as-you-go per generated video. For image tasks, gpt-image-2 charges only on input (image output is free), image to image starts at about ¥0.035, and 4K output is priced the same as 1K output. See relaydance.com/models for current rates.

FAQ

How many reference images can one request use? A single request accepts up to 9 reference images, plus up to 3 reference videos and 3 audio tracks, with clips up to 15 seconds.

Am I charged for a failed generation? No. According to the official documentation, "failed or errored requests are never billed"(According to the official relaydance.com docs).

Do I need a new SDK? No. The API is OpenAI compatible; change the base URL to https://relaydance.com/v1 and keep the OpenAI SDK.