Text to video API quickstart with an OpenAI compatible endpoint

RelayDance is an OpenAI compatible AI video generation API that lets you generate video with Seedance and related models by pointing the OpenAI SDK at https://relaydance.com/v1. You authenticate with a Bearer API key, submit a task to POST /v1/video/generations, then poll GET /v1/video/generations/{task_id} until the status is succeeded or failed. Billing is pay-as-you-go, and failed or errored requests are never billed (see relaydance.com/models).

How do I connect to the endpoint?

You connect by changing the base URL in your existing OpenAI SDK and supplying a Bearer key. According to the official relaydance.com docs,"set base_url to https://relaydance.com/v1 and keep your OpenAI SDK". Create keys in the console at https://relaydance.com/console and send them as Authorization: Bearer YOUR_API_KEY. The interface is OpenAI compatible, so you reuse client libraries without a separate integration layer. This provides direct access to Seedance with no BytePlus enterprise account or KYC required. Reference the full protocol at relaydance.com/docs, including video, image, and webhook flows.

What are the steps to generate a video?

You generate a video in three steps: submit, poll, and read the result URL.

1. Submit with POST /v1/video/generations, passing model, prompt, seconds, and metadata (ratio, resolution, generate_audio, callback_url, content[] reference media).
2. Poll GET /v1/video/generations/{task_id} until status is succeeded or failed; the response then contains the video url.
3. Alternatively, set metadata.callback_url to use webhook mode, where the final state is POSTed to your server.

Reference media go in metadata.content[] and are cited in the prompt as @image1 to @imageN. Each request accepts up to 9 reference images, 3 reference videos, and 3 audio tracks, with clips up to 15 seconds.

How much does each model cost?

Pricing is per second or per clip and varies by model and resolution, per relaydance.com/models.

For images, gpt-image-2 charges only for input: image output is free, image to image starts at about ¥0.035, and 4K output is priced the same as 1K output. Live per-model rates remain at relaydance.com/models.

How does billing handle failed requests?

Failed requests are not billed, so you pay only for successful generations. According to the official relaydance.com docs,"failed or errored requests are never billed". Billing is pay-as-you-go per generated video, which means a request that returns an error status carries no charge. Payments are supported through USDT and Stripe card. With Seedance 2.0 720p at about $0.190 / second and Seedance Fast at about $0.152 / second, costs scale with the number of generated seconds rather than with attempts, and an errored job is excluded from the total.

FAQ

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

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

Which payment methods are accepted? USDT and Stripe card, billed pay-as-you-go per generated video.