Skip to navigation

Seedance Video Models

View as Markdown

Use POST /videos to create a Seedance video generation task. The example includes optional route and route_mode fields; remove them to use the default available route.

curl -s https://api.getopenmodels.com/v1/videos \
-H "Authorization: Bearer $OM_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "doubao-seedance-2.0-fast",
"route": { "provider": "<provider-for-this-model>" },
"route_mode": "balanced",
"content": [
{
"type": "text",
"text": "Generate a video of a carp leaping over the Dragon Gate."
}
],
"generate_audio": true,
"resolution": "720p",
"ratio": "16:9",
"duration": 5,
"watermark": false
}'

Use the returned ID to retrieve the task status and generated video result.

curl "https://api.getopenmodels.com/v1/videos/{id}" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OM_API_KEY"

For Seedance 2.0 models, set generation options in the request body. Current supported model IDs are doubao-seedance-2.0-fast and doubao-seedance-2.0.

FieldTypeNotes
modelstringUse doubao-seedance-2.0-fast or doubao-seedance-2.0.
contentarrayInput content. Include at least one text item with the video prompt.
generate_audiobooleanWhether to generate synchronized audio. Default: true.
resolutionstringOutput resolution. Default: 720p. Use 480p or 720p for the fast model. The standard doubao-seedance-2.0 model can also use higher-resolution modes such as 1080p and 4k.
ratiostringOutput aspect ratio. Valid values: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive. Default: adaptive.
durationintegerOutput duration in seconds. Default: 5. Valid range: 4-15, or -1 to let the model decide.
watermarkbooleanWhether to add the AI-generated watermark. Default: false.

frames, seed, and camera_fixed are not supported by the current Seedance 2.0 models.