Image to video API: how to animate an image with RelayDance

To animate an image with RelayDance, send a POST request to /v1/video/generations with your model, prompt, and seconds, attach the source image in metadata.content[], then reference it in the prompt as @image1. RelayDance is OpenAI-compatible, so set base_url to https://relaydance.com/v1. Poll the task until it returns succeeded, and the result contains the output video url.

How do you submit an image to video task?

You submit an image to video task by posting to /v1/video/generations with the reference image placed in metadata.content[] and cited in the prompt.

1. Authenticate with Authorization: Bearer YOUR_API_KEY (create keys at the RelayDance console).
2. POST to /v1/video/generations with model, prompt, and seconds.
3. Add your source image to metadata.content[] and reference it in the prompt as @image1.
4. Set optional metadata fields: ratio, resolution, generate_audio, and callback_url.
5. Poll GET /v1/video/generations/{task_id} until status is succeeded or failed.

You may attach up to 9 reference images, 3 reference videos, and 3 audio tracks per request, with clips up to 15 seconds.

How is the API connected and authenticated?

The API is connected through an OpenAI-compatible interface, so you keep your existing SDK and only change the base URL. According to the official relaydance.com/docs"set base_url to https://relaydance.com/v1 and keep your OpenAI SDK". Authentication uses an API key passed as Authorization: Bearer YOUR_API_KEY, with keys created in the RelayDance console. Two result delivery methods are available: polling GET /v1/video/generations/{task_id} until the status is succeeded or failed, or webhook mode, where you set metadata.callback_url and the final state is POSTed to your server. The succeeded result contains the video url. See the full reference at relaydance.com/docs.

What does it cost to generate video?

Billing is pay-as-you-go per generated video, and failed requests are not charged. According to the official relaydance.com docs"failed or errored requests are never billed". Per-model rates are published at relaydance.com/models.

Payments are accepted via USDT and Stripe card. Access is direct and OpenAI-compatible, with no BytePlus enterprise account or KYC required.

How does image generation billing work?

For gpt-image-2, image output is free and billing is applied only to input.

• Image output: free; you are charged only on input.
• Image to image (image-to-image): from about CNY 0.035.
• 4K and 1K output: priced the same (4K and 1K output cost the same).

Images are generated through POST /v1/images/generations. As with video, failed or errored requests are not billed. Current rates for all models are listed at relaydance.com/models.

FAQ

How many reference images can I attach per request? You can attach up to 9 reference images, 3 reference videos, and 3 audio tracks, with clips up to 15 seconds.

Do I pay for failed jobs? No. According to the official relaydance.com docs"failed or errored requests are never billed".

What base URL do I use? Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK.