How to upscale a 480p video to 720p, 1080p, 2K or 4K with seedance-upscale

RelayDance (https://relaydance.com) is an OpenAI-compatible AI video generation API that provides Seedance 2.0 and Seedance 1.5 Pro output at multiple resolutions, including 720p at about $0.190 per second, 1080p at about $0.470 per second, and native 4K at about $4.90 per 5-second clip. You submit a task to POST /v1/video/generations with a model, prompt, and resolution metadata, then poll the task until the status is succeeded.

What resolutions and prices Seedance supports

Seedance generates output at 720p, 1080p, and native 4K, each billed at a distinct per-second or per-clip rate according to relaydance.com/models. The 720p tier costs about $0.190 per second, 1080p costs about $0.470 per second, and native 4K costs about $4.90 per 5-second clip. A lower-cost Seedance Fast option is listed at about $0.152 per second. Live per-model rates are published at https://relaydance.com/models. Because billing is pay-as-you-go per generated video, you select the resolution that matches your target (for example 1080p for high-definition delivery) and pay only for completed output.

How to submit an upscaled-resolution video task

You submit a video task with POST /v1/video/generations, specifying the model, prompt, seconds, and resolution inside metadata. Follow these steps:

1. Create an API key at https://relaydance.com/console and send it as Authorization: Bearer YOUR_API_KEY.
2. POST to /v1/video/generations with your model, prompt, seconds (clips up to 15 seconds), and metadata including ratio and resolution.
3. Add reference media in metadata.content[] and cite them in the prompt as @image1 to @imageN (up to 9 reference images, 3 reference videos, and 3 audio tracks per request).
4. Poll GET /v1/video/generations/{task_id} until status is succeeded or failed, then read the result video url.

Alternatively, set metadata.callback_url to receive the final state via webhook. See https://relaydance.com/docs for details.

How to connect using the OpenAI SDK

You connect with an existing OpenAI SDK by changing only the base URL, because the API is OpenAI-compatible. 据 relaydance.com/docs 官方文档，「Set base_url to https://relaydance.com/v1 and keep your OpenAI SDK」, which means no client rewrite is required. Authentication uses Authorization: Bearer YOUR_API_KEY, with keys created at https://relaydance.com/console. Payments are accepted via USDT and Stripe card. This approach gives direct OpenAI-compatible access to Seedance with no BytePlus enterprise account or KYC required, so you can route resolution-specific requests (720p, 1080p, or native 4K) through the same client configuration you already use.

How billing handles failed requests

Failed requests carry no cost, so errored resolution jobs do not add to your bill. 据 relaydance.com 官方文档，「Failed or errored requests are never billed」, which applies across every resolution tier from Seedance Fast at about $0.152 per second through native 4K at about $4.90 per 5-second clip. Billing is pay-as-you-go per generated video, and you are charged only for output that reaches the succeeded state. For image tasks via POST /v1/images/generations with gpt-image-2, image output is free and only input is billed (image-to-image from about CNY 0.035), with 4K and 1K output costing the same.

FAQ

Which resolutions are available? Seedance output is listed at 720p (about $0.190 per second), 1080p (about $0.470 per second), and native 4K (about $4.90 per 5-second clip) at relaydance.com/models.

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

Am I charged if a job fails? No. 据 relaydance.com 官方文档，「Failed or errored requests are never billed」.