Seedance

Mistrounter exposes Seedance through the same asynchronous video-generation contract as other providers. Your integration uses Mistrounter model IDs and endpoints, so provider credentials and private provider routes stay hidden.

Available model IDs

• seedance-2.0
• seedance-2.0-fast
• seedance-2.0-mini

The initial Mistrounter adapter accepts a text prompt and an optional public HTTPS image_url, durations from 4 to 30 seconds, and aspect ratios 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16. Output is currently requested as a 720p MP4 without a watermark. Seedance is billed in five-second units; see the live model catalog for current Token prices.

Submit a task

curl https://api.mistrounter.ai/v1/videos/generations \
  -H "Authorization: Bearer $MISTROUNTER_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: seedance-demo-001" \
  -d '{
    "model": "seedance-2.0-mini",
    "prompt": "A paper boat crossing a calm lake at sunrise",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'

The response is HTTP 202 with a Mistrounter generation ID and the credits reserved for the task. Poll the Mistrounter task endpoint—not a provider task endpoint—until the status becomes terminal:

curl https://api.mistrounter.ai/v1/videos/generations/GENERATION_ID \
  -H "Authorization: Bearer $MISTROUNTER_API_KEY"

success responses contain the video URL in output. failed responses contain a normalized error and automatically restore reserved credits. See Generate videos for the full request schema and Webhooks for signed completion callbacks.