Seedance 2.5 API — 30-Second Multimodal Reference Video

Generate 4-30 second videos with multimodal reference input using Seedance 2.5 through VicSee API. Text, image, video, and audio references. 480p and 720p with native audio. 148-2500 credits.

Longest durations available. Seedance 2.5 generates up to 30 seconds in a single request — more than double the 15-second ceiling of the rest of the Seedance family. Generation time scales with length; a short clip typically takes several minutes.

Pricing

Billed by duration and resolution. Every integer duration from 4 to 30 seconds is available.

Duration	480p Credits	720p Credits
4s	148	333
5s	185	417
6s	222	500
7s	259	583
8s	296	667
9s	333	750
10s	370	833
11s	407	917
12s	444	1000
13s	481	1083
14s	519	1167
15s	556	1250
16s	593	1333
17s	630	1417
18s	667	1500
19s	704	1583
20s	741	1667
21s	778	1750
22s	815	1833
23s	852	1917
24s	889	2000
25s	926	2083
26s	963	2167
27s	1000	2250
28s	1037	2333
29s	1074	2417
30s	1111	2500

Video reference pricing

Supplying a video reference switches the whole request to per-second billing:

credits = rate x (input video seconds + output seconds)

Resolution	Rate
480p	22.5 credits/second
720p	50.3 credits/second

Image and audio references do not change the billing model — those requests use the flat duration table above.

Seedance 2.5 does not offer 1080p or 4K. For higher resolutions use Seedance 2.0, which supports 1080p and 4K at 4-15 seconds.

Endpoint

POST https://vicsee.com/api/v1/generate

See Authentication for API key setup.

Text to Video

Generate videos from text descriptions with native audio.

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	`seedance-2-5-text-to-video`
input.prompt	string	Yes	Video description (max 30,000 chars)
input.duration	number	No	4-30 seconds, any integer (default: 5)
input.resolution	string	No	`480p`, `720p` (default: 720p)
input.aspect_ratio	string	No	`16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `21:9`, `adaptive` (default: adaptive)
input.audio	boolean	No	Enable native audio (default: true)
input.web_search	boolean	No	Enhance prompt with web search (default: false)
input.nsfw_checker	boolean	No	NSFW content filter (default: true). VicSee always sends `true` unless explicitly overridden.

Example Request

curl -X POST https://vicsee.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2-5-text-to-video",
    "input": {
      "prompt": "A martial arts master demonstrates fluid spear techniques in a sunlit courtyard",
      "duration": 15,
      "resolution": "720p",
      "aspect_ratio": "adaptive",
      "audio": true
    }
  }'

Image to Video

Animate images into video using first frame and optional last frame control.

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	`seedance-2-5-image-to-video`
input.prompt	string	Yes	Motion description (max 30,000 chars)
input.image_urls	array	Yes	1-2 images: first frame, optional last frame. Max 30MB each
input.duration	number	No	4-30 seconds, any integer (default: 5)
input.resolution	string	No	`480p`, `720p` (default: 720p)
input.aspect_ratio	string	No	`16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `21:9`, `adaptive` (default: adaptive)
input.audio	boolean	No	Enable native audio (default: true)

Input images must have an aspect ratio between 0.4 and 2.5 (width divided by height) and at most 36 megapixels in total.

Example Request

curl -X POST https://vicsee.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2-5-image-to-video",
    "input": {
      "prompt": "The camera slowly pushes in as the subject turns toward the light",
      "image_urls": ["https://example.com/first-frame.jpg"],
      "duration": 10,
      "resolution": "720p"
    }
  }'

Reference to Video

Drive generation with image, video, and audio references. Refer to images positionally in the prompt as @Image1, @Image2, and so on.

Request Parameters

Parameter	Type	Required	Description
model	string	Yes	`seedance-2-5-reference-to-video`
input.prompt	string	Yes	Description referencing inputs as `@Image1`, `@Image2`, … (max 30,000 chars)
input.reference_image_urls	array	Yes	Up to 30 images. Max 30MB each
input.reference_video_urls	array	No	Video references. Max 200MB each, 30 seconds total across all videos
input.reference_audio_urls	array	No	Audio references. Max 15MB each, 30 seconds total across all clips
input.duration	number	No	4-30 seconds, any integer (default: 5)
input.resolution	string	No	`480p`, `720p` (default: 720p)
input.aspect_ratio	string	No	`16:9`, `9:16`, `1:1`, `4:3`, `3:4`, `21:9`, `adaptive` (default: adaptive)
input.audio	boolean	No	Enable native audio (default: true)

Adding a video reference changes billing to per-second across the input and output combined. A 4-second output with a 6-second reference video at 480p costs 22.5 x (6 + 4) = 225 credits, not the 148 shown in the duration table.

Example Request

curl -X POST https://vicsee.com/api/v1/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2-5-reference-to-video",
    "input": {
      "prompt": "@Image1 walks through the alley in @Image2, handheld camera following behind",
      "reference_image_urls": [
        "https://example.com/character.png",
        "https://example.com/setting.png"
      ],
      "duration": 12,
      "resolution": "720p"
    }
  }'

Response

All three modes return a task immediately. Poll /api/v1/tasks/{id} until the status is completed or failed.

{
  "success": true,
  "data": {
    "id": "8a46e9c3-b30d-44b7-8c74-74d3085d691c",
    "model": "seedance-2-5-reference-to-video",
    "status": "pending",
    "creditsUsed": 135,
    "creditsRemaining": 19726,
    "createdAt": "2026-08-10T14:10:50.394Z"
  }
}

Seedance 2.0 - 4-15 seconds, adds 1080p and 4K
Seedance 2.0 Fast - Same capabilities as 2.0, cheaper and faster for drafting
Seedance 1.5 Pro - Up to 1080p, multilingual audio, no reference mode

Seedance 2.5

On this page