Skip to main content
Seedance 2.0 is a video model family for text-to-video, image-to-video, reference-to-video, video editing, and video extension workflows. Use product-level model IDs in model, then choose the workflow with operation.

​
Model Choice

ModelBest forPublic resolutionsReference inputs
seedance-2.0Highest quality and 4K output480p, 720p, 1080p, 4kUp to 9 reference images plus up to 3 reference videos and 3 reference audios for reference-to-video
seedance-2.0-fastFaster, lower-cost 480p/720p output480p, 720pUp to 9 reference images plus up to 3 reference videos and 3 reference audios for reference-to-video
seedance-2.0-miniLowest-cost 480p/720p output480p, 720pSupports the Seedance 2.0 operation family; read the current model detail before relying on exact reference count limits
seedance-2.0-fast and seedance-2.0-mini are fail-closed to 480p / 720p; do not send 1080p or 4k to those models.

​
Supported Operations

The public Seedance 2.0 family supports:
OperationTypical inputs
text-to-videoprompt
image-to-videoprompt, image_url or compatible image input
start-end-to-videoprompt, start_image, end_image
reference-to-videoprompt, reference_images, optional video_urls, optional audio_urls
video-to-videoprompt, video_url or compatible video input
video-extensiontask_id or model-specific continuation input
Pure audio-only and text-plus-audio-only Seedance requests are not part of the public contract. Use audio as a reference input only in supported reference-to-video flows.

​
4K Reference-To-Video

Use seedance-2.0 when you need 4K output. The base model supports 4k across the governed public contract, including reference-to-video. 
curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0",
    "operation": "reference-to-video",
    "prompt": "Keep the same product identity and lighting while creating a slow cinematic rotation.",
    "reference_images": [
      "https://example.com/product-front.jpg",
      "https://example.com/product-side.jpg"
    ],
    "video_urls": ["https://example.com/motion-reference.mp4"],
    "duration": 6,
    "resolution": "4k",
    "aspect_ratio": "16:9"
  }'

​
Fast And Mini Requests

Use seedance-2.0-fast when latency matters, and seedance-2.0-mini when the lowest cost tier is more important than maximum quality. 
curl -X POST "https://api.tokenlab.sh/v1/videos/generations" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.0-fast",
    "operation": "text-to-video",
    "prompt": "A clean product reveal on a white studio background, gentle camera push-in.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }'

​
Pricing And Billing

Seedance 2.0 pricing is token-based and depends on output resolution and whether the request includes video input. TokenLab’s USD price truth for these models is converted from official CNY pricing using 6.8 CNY per USD. Use the Pricing API or Models API for the current billable price before hard-coding product UI.

​
Async Results

Video generation is asynchronous. Follow the poll_url returned by the create request, or use GET /v1/tasks/{id} with the returned task ID. See Create Video, Get Task Status, and Cancel Task for endpoint details.