Video model by ByteDance

Seedance 2.0 Mini API

model: seedance-2.0-mini

Call Seedance 2.0 Mini with your KeelRouter API key, the same key you use for every other model. From $0.023 per second, paid per call from a prepaid balance. Failed calls are free.

Pricing

OptionPrice
480p$0.023 per second
720p$0.051 per second

Call it

Async: POST /v1/video/generations returns a taskId; poll the same path with ?task_id= or pass a callback_url.

curl https://api.keelrouter.com/v1/video/generations \
  -H "Authorization: Bearer $KEELROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "seedance-2.0-mini",
  "prompt": "A paper boat drifting down a rainy street, slow camera follow",
  "resolution": "480p"
}'

Parameters

NameTypeNotes
modelstringRequired. seedance-2.0-mini
promptstring
resolutionstringOne of 480p, 720p. Default 720p.
aspect_ratiostringOne of adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16. Default adaptive.
durationnumberRange 4–15. Default 5.
generate_audiobooleanDefault true.
first_frame_urlstring
last_frame_urlstring
reference_image_urlsarray
reference_video_urlsarray
reference_audio_urlsarray
web_searchboolean
callback_urlstringOptional https URL; we POST the result when the task ends

FAQ

How much does the Seedance 2.0 Mini API cost on KeelRouter?
From $0.023 per second. You pay per call from a prepaid USD balance; failed calls are not charged.
How do I call Seedance 2.0 Mini?
POST to /v1/video/generations with model "seedance-2.0-mini". You get a taskId back; poll the same endpoint with ?task_id= or pass a callback_url.
Is this the official Seedance 2.0 Mini API?
No. KeelRouter is an independent API gateway. Requests run on Seedance 2.0 Mini through our upstream providers, and the video model keeps its own safety filters.
How long are results kept?
Result files are kept for 30 days, then deleted. Download what you want to keep.

More from ByteDance

KeelRouter is an independent service and is not affiliated with ByteDance. Seedance 2.0 Mini is a trademark of its owner, used here only to name the model a request runs on.