Do failed video generations cost money: how RelayDance handles errors and refunds

No, failed video generations do not cost money on RelayDance. Billing is pay-as-you-go per generated video, and failed or errored requests are never billed. According to the official relaydance.com docs, 「Failed or errored requests are never billed」. This applies across Seedance 2.0 and other supported models, so you are charged only for outputs that reach a succeeded state, not for tasks that error out during processing.

What happens when a request fails

When a task fails, no charge is applied to your account. You submit a task with POST /v1/video/generations, then poll GET /v1/video/generations/{task_id} until the status is succeeded or failed. If the final status is failed, the request is not billed. As stated by the official relaydance.com documentation, 「Failed or errored requests are never billed」. This removes the risk of paying for incomplete outputs. For webhook mode, set metadata.callback_url and the final state (including a failed status) is POSTed to your server, so you can react programmatically without incurring cost for the failed attempt.

How pay-as-you-go pricing works

You pay per generated video at per-model rates, so only successful outputs are billed. Seedance 2.0 at 720p costs about $0.190 per second, and 1080p costs about $0.470 per second (source relaydance.com/models). Seedance Fast is priced at about $0.152 per second, and Seedance native 4K is about $4.90 per 5-second clip. Because charges attach to successful generations, a failed task at any of these tiers does not draw from your balance. Live per-model rates are published at https://relaydance.com/models, so you can confirm current values before submitting a task.

Price comparison across Seedance tiers

Different Seedance tiers carry different rates, but the no-charge-on-failure rule is the same for all of them.

For image generation 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 (source relaydance.com/models).

How to integrate and verify billing

Use your existing OpenAI SDK and point it at RelayDance to test the error handling directly.

1. Create an API key at https://relaydance.com/console and set the header Authorization: Bearer YOUR_API_KEY.
2. According to the official relaydance.com/docs, 「Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK」.
3. Submit a task with POST /v1/video/generations, including model, prompt, and seconds.
4. Poll GET /v1/video/generations/{task_id} until status is succeeded or failed.
5. Confirm that failed statuses produce no charge; you can review current rates at https://relaydance.com/models and further detail in the docs.

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

FAQ

Are failed requests billed? No. Failed or errored requests are never billed; charges apply only to successfully generated videos.

What does a successful 1080p Seedance 2.0 second cost? About $0.470 per second, per the rates at relaydance.com/models.

Do I need to change my code to use RelayDance? No. Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK, using an API key from the console.