how to use Seedance API: submit, poll, and handle the failure case

Submit

curl -X POST https://genace.ai/api/v1/video/generations \
  -H "Authorization: Bearer $GENACE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"seedance-2.0-fast","prompt":"..."}'

The model id is exactly seedance-2.0-fast — a typo here returns 400 UNKNOWN_MODEL naming what you sent.

You get 202 Accepted with a job, not a video:

{
  "job_id": "abc123",
  "state": "queued",
  "model": "seedance-2.0-fast",
  "credits_held": 25
}

credits_held is what this call reserved. It comes back in full if the job fails or you cancel it.

Collect the result

curl "https://genace.ai/api/v1/jobs/abc123?wait=30" \
  -H "Authorization: Bearer $GENACE_API_KEY"

wait holds a status request for the requested bounded interval. Poll the known job ID or read the authenticated SSE stream, then reconnect if needed. The scheduled backstop is internal, not a customer delivery channel. There is no customer callback URL field on the generation request. See webhook vs polling.

The failure that will not throw

A failed job is a successful HTTP response describing a failure:

{ "state": "failed", "error": { "code": "UPSTREAM_EMPTY_RESULT" } }

raise_for_status() and equivalents see a 200 and move on. Check state, not the status code.

Parameters worth setting

duration_sec accepts 3–15. Setting resolution to 720p halves the cost while you iterate.

Full reference in Seedance 2.0 Fast API parameters.

Continue with models and parameters

• Flux API key: two paths, and what changes after you have one
• Flux API parameters: every accepted value and what it costs
• Flux aspect ratio options: what it accepts and what it rejects
• Browse all models and parameters guides

Models covered on this page

• Seedance 2.0