Seedance 2.5 Draft Final Serverless API
Finalize 480p drafts to 1080p video with native audio.
POST /v2/seedance-2.5-draft-final · submit + poll 1# pip install "segmind>=1.1.0"
2# export SEGMIND_API_KEY="YOUR_API_KEY"
3from segmind import SegmindClient, InferenceFailed, InferenceTimeout
4
5# Async (v2) — recommended for long-running / video models.
6# run() blocks up to 600s; submit_async + job.wait(timeout=...) sets a longer
7# deadline and keeps the request_id so you can re-poll later.
8client = SegmindClient() # reads SEGMIND_API_KEY
9payload = {
10 "draft_task_id": "cgt-YOUR-DRAFT-TASK-ID",
11 "output_format": "mp4",
12 "return_last_frame": False,
13 "output_codec": "h264",
14}
15job = client.submit_async("seedance-2.5-draft-final", **payload)
16print(job.request_id) # available immediately
17try:
18 result = job.wait(timeout=900, interval=2.0)
19 print(result["status"]) # COMPLETED
20 print(result.get("output")) # model output (e.g. video URL)
21except InferenceTimeout as e:
22 print("still running:", e.request_id) # re-poll later with this id
23except InferenceFailed as e:
24 print("failed:", e.detail)
25
26# Fast models (<=600s) can use the one-liner instead:
27# result = segmind.run("seedance-2.5-draft-final", **payload) 1# pip install "segmind>=1.1.0"
2# export SEGMIND_API_KEY="YOUR_API_KEY"
3from segmind import SegmindClient, InferenceFailed, InferenceTimeout
4
5# Async (v2) — recommended for long-running / video models.
6# run() blocks up to 600s; submit_async + job.wait(timeout=...) sets a longer
7# deadline and keeps the request_id so you can re-poll later.
8client = SegmindClient() # reads SEGMIND_API_KEY
9payload = {
10 "draft_task_id": "cgt-YOUR-DRAFT-TASK-ID",
11 "output_format": "mp4",
12 "return_last_frame": False,
13 "output_codec": "h264",
14}
15job = client.submit_async("seedance-2.5-draft-final", **payload)
16print(job.request_id) # available immediately
17try:
18 result = job.wait(timeout=900, interval=2.0)
19 print(result["status"]) # COMPLETED
20 print(result.get("output")) # model output (e.g. video URL)
21except InferenceTimeout as e:
22 print("still running:", e.request_id) # re-poll later with this id
23except InferenceFailed as e:
24 print("failed:", e.detail)
25
26# Fast models (<=600s) can use the one-liner instead:
27# result = segmind.run("seedance-2.5-draft-final", **payload)API Endpoint
https://api.segmind.com/v1/seedance-2.5-draft-finalParameters
draft_task_idrequiredstringThe draft_task_id returned by a seedance-2.5 render made with draft: true (response header X-Draft-Task-ID, or video.draft_task_id on /v2). Valid for 7 days. The prompt, reference media, duration, aspect ratio, seed, audio setting and task type are inherited from the draft and cannot be changed here.
output_codecoptionalstringCodec of the delivered file. The final render is 1080p, which BytePlus encodes as 10-bit HEVC: 'auto' returns that master untouched (Chrome and Firefox on Windows cannot decode it and will play audio over a blank frame); 'h264' re-encodes it to H.264 High 8-bit yuv420p, which plays everywhere, at the cost of one more generation of compression and half the bit depth. Does not affect price.
"auto""auto""h264"output_formatoptionalstringmp4 = best compatibility. mov (H.264 + yuv444p + PCM) = higher color fidelity; recommended for video editing/extension round-trips.
"mp4""mp4""mov"return_last_frameoptionalbooleanReturns the final video frame as a separate image, delivered in the response as `video.last_frame_url`. Chain shots by feeding that URL into the next generation's `first_frame_url`. Note this is an output: it is distinct from the `last_frame_url` input parameter, which is an image you supply to steer how the clip ends.
falseResponse Type
Returns: Video
Asynchronous requests (v2)
Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.
- 1
POST /v2/seedance-2.5-draft-finalSubmit — returns request_id, status_url, response_url
- 2
GET /v2/requests/{id}/statusPoll — until COMPLETED or FAILED
- 3
GET /v2/requests/{id}Result — final response body
Status states
- A FAILED request is served as HTTP 422 — the body still carries the error detail.
- An unknown or expired request_id returns HTTP 404.
- Results are retained for 1 hour, then expire.
- Content / RAI blocks surface as FAILED, not a separate state.
- Track completion by polling the status endpoint.
Common Error Codes
The API returns standard HTTP status codes. Detailed error messages are provided in the response body.
Bad Request
Invalid parameters or request format
Unauthorized
Missing or invalid API key
Forbidden
Insufficient permissions
Not Found
Model or endpoint not found
Insufficient Credits
Not enough credits to process request
Rate Limited
Too many requests
Server Error
Internal server error
Bad Gateway
Service temporarily unavailable
Timeout
Request timed out