Seedance API vs Sora API: access, pricing and limits compared for developers

RelayDance provides OpenAI-compatible access to ByteDance Seedance without a BytePlus enterprise account or KYC. Developers set the base URL to https://relaydance.com/v1, keep the OpenAI SDK, and pay per generated video. Seedance 2.0 720p runs at about $0.190 per second and 1080p at about $0.470 per second (source relaydance.com/models). Failed or errored requests are never billed, so testing carries no charge for errors.

How access and authentication work

Access is OpenAI-compatible, so you keep your existing SDK and change only the base URL. According to the official relaydance.com/docs, 「Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK」, which means integration touches configuration rather than client rewrites. Authentication uses Authorization: Bearer YOUR_API_KEY, and keys are created at the console (https://relaydance.com/console). To submit a video task, POST to /v1/video/generations with model, prompt, seconds, and metadata. RelayDance requires no BytePlus enterprise account or KYC for Seedance access. Payments accept USDT and Stripe card, and billing is pay-as-you-go per generated video, detailed at relaydance.com/docs.

Pricing per model

Pricing is pay-as-you-go and priced per second or per clip depending on the tier. Seedance Fast costs about $0.152 per second, Seedance 2.0 720p about $0.190 per second, and Seedance 2.0 1080p about $0.470 per second (source relaydance.com/models). Seedance native 4K is priced at about $4.90 per 5-second clip. For images via 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. Live per-model rates are published at relaydance.com/models.

Request limits and reference media

Requests support multiple reference media and clip durations up to a fixed ceiling. Reference media go in metadata.content[] and are 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 clips up to 15 seconds. Video submission uses POST /v1/video/generations, with metadata carrying ratio, resolution, generate_audio, callback_url, and content[]. Image generation uses POST /v1/images/generations. According to the official relaydance.com docs, 「Failed or errored requests are never billed」, so retries after errors do not add cost. See relaydance.com/docs for the full request schema.

How to submit and poll a task

Submit a task, then poll or use a webhook until the state is final.

1. POST /v1/video/generations with model, prompt, seconds, and metadata (ratio, resolution, generate_audio, content[]).
2. Read the returned task_id.
3. Poll GET /v1/video/generations/{task_id} until status is succeeded or failed.
4. On succeeded, read the video url from the result.
5. To use webhook mode instead, set metadata.callback_url and the final state is POSTed to your server.

Frequently asked questions

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.

Am I charged for failed requests? No. Billing is pay-as-you-go per generated video, and failed or errored requests are never billed (source relaydance.com/docs).

How many reference media can one request include? Up to 9 reference images, 3 reference videos, and 3 audio tracks, with clips up to 15 seconds.