Skip to main content
POST
Pricing: See vibetool.ai/pricing for current rates.
Seedance 2.0 is ByteDance’s second-generation video model for multimodal video generation. It accepts a text prompt along with an optional reference image or video to guide the output. The model is billed per second of generated video.

Authorization

string
required
All APIs require Bearer Token authentication. Format: Bearer YOUR_API_KEY

Request Body

string
required
Model identifier. Must be seedance-2.0-fast-reference-to-video.
string
required
A text description of the video to generate. For example, "A serene mountain landscape at sunset, with clouds drifting slowly".Maximum length: 1000 characters.
string
URL of a reference image to guide the video content. Optional.
string
URL of a reference video to influence motion or style. Optional.
integer
Seed for deterministic generation. If omitted, a random seed is used.Range: 0 to 2147483647

Response Schema

string
required
Unique task ID. Use this to poll for the generated video via the status endpoint.
enum<string>
required
Initial task status. Always pending immediately after creation.Available options: pending, processing, completed, failed
integer
Unix timestamp (seconds) when the task was created.
number
Approximate duration of the final video in seconds. Useful for billing estimates.

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
model
enum<string>
required

Use seedance-2.0-fast-reference-to-video.

Available options:
seedance-2.0-fast-reference-to-video
prompt
string
required

Text description of the video to generate

image_url
string<uri>

Reference image URL

video_url
string<uri>

Reference video URL

seed
integer

Random seed for reproducibility

Response

Task created

id
string

Unique identifier for the generation task

object
string
Example:

"video.generation"

model
string
created_at
integer

Unix timestamp (seconds)

status
enum<string>

Initial task status

Available options:
pending,
processing
task_id
string

Task ID for the status polling endpoint