Seedance 2.0 Fast

Fast AI video generation from text, images, video, or audio references. Lower cost, faster output. 4-15 seconds.

POST/v1/media/queue

~$1.20 est.

Overview

Fast video generation with same capabilities as Seedance 2.0 at lower cost and faster speed. Async operation — submit a job, poll for completion.

Property	Value
Model ID	`bytedance/seedance-2-0-fast`
Upstream Model	`dreamina-seedance-2-0-fast-260128`
Resolutions	480p, 720p
Duration	4–15 seconds (continuous)
Aspect Ratios	21:9, 16:9, 4:3, 1:1, 3:4, 9:16
Audio Generation	Optional (built-in)
Billing	Token-based (dynamic)
Pricing	~$11.2/1M tokens

Usage

All media models use the async job queue. Submit a job, then poll for the result.

Step 1: Submit Job

const res = await fetch('https://api.yepapi.com/v1/media/queue', {
  method: 'POST',
  headers: {
    'x-api-key': 'YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'bytedance/seedance-2-0-fast',
    prompt: 'Close-up of rain falling on a calm pond, concentric ripples, mist rising',
    options: {
      aspectRatio: '16:9',
      duration: '5',
    },
  }),
});
const { data } = await res.json();
// data.jobId — use this to poll for results

curl -X POST https://api.yepapi.com/v1/media/queue \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "bytedance/seedance-2-0-fast", "prompt": "Close-up of rain falling on a calm pond", "options": {"aspectRatio": "16:9", "duration": "5"}}'

Step 2: Poll for Result

const status = await fetch(`https://api.yepapi.com/v1/media/status/${data.jobId}`, {
  headers: { 'x-api-key': 'YOUR_API_KEY' },
});
const { data: job } = await status.json();
// job.status — "pending" | "processing" | "completed" | "failed"
// job.result.video — { mimeType, base64 } when completed

curl https://api.yepapi.com/v1/media/status/JOB_ID \
  -H "x-api-key: YOUR_API_KEY"

Request Body

Parameter	Type	Required	Description	Default
`model`	`string`	Yes	`bytedance/seedance-2-0-fast` or alias `seedance-fast`	—
`prompt`	`string`	Yes	Text description of the video to generate	—
`options.aspectRatio`	`string`	No	`21:9`, `16:9`, `4:3`, `1:1`, `3:4`, or `9:16`	`16:9`
`options.duration`	`string`	No	`4` to `15` (seconds)	`5`
`options.generateAudio`	`boolean`	No	Generate audio track for the video	`false`
`options.watermark`	`boolean`	No	Add watermark to output	`false`
`options.imageRole`	`string`	No	How to use the input image: `first_frame`, `last_frame`, or `reference_image`	`first_frame`
`options.referenceVideoUrl`	`string`	No	URL of a reference video for style/motion guidance	—
`options.referenceAudioUrl`	`string`	No	URL of a reference audio track	—
`imageData.mimeType`	`string`	No	MIME type of input image	—
`imageData.base64`	`string`	No	Base64-encoded input image for image-to-video	—

Pricing

Token-based billing. Cost varies by resolution and duration.

Metric	Cost
Per 1M tokens	$11.20
Typical 5s video (720p)	~$1.20

Info

Latency: typically 15-60 seconds. Results retained for 1 hour.

Under the Hood