sume/auto or a pinned video model: how to decide
Use sume/auto when you accept 3 to 10 second clips at 16:9 or 9:16 and do not care which family runs. Pin a model id for a specific input, length or audio.

Use sume/auto when you want Sume to choose the family and you can live with its create controls: 720p and 8 seconds by default, 3 to 10 second clips at 16:9 or 9:16. Pin a model id such as kling-3 or seedance-2.5 when you need a specific input (frames, references), a longer clip or a set audio behavior. The response to an Auto job echoes sume/auto and Sume does not disclose which family ran.
Read from Video generation and Video Router, 2026-09-29.
What does sume/auto give me?
| Question | `sume/auto` | Pinned id |
|---|---|---|
| Who picks the family | Sume | You |
Response model | Echoes sume/auto | Your id |
| Defaults | 720p, 8 s | Per model |
| Clip length | 3 to 10 s | Per model, up to 30 s |
| Aspect ratios | 16:9, 9:16 | Per model |
| 4K | Yes, on /v1/videos | gemini-omni-flash-1.1 |
| Replays | Route and price identically | Same job returned |
How do I send an Auto request?
Poll GET /v1/videos/{id} as with any model.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: auto-001" \
-d '{
"model": "sume/auto",
"prompt": "A vertical UGC-style product clip on a desk, natural light",
"aspect_ratio": "9:16",
"duration": 5
}'When should I pin?
- You need
first_frameandlast_frameon a chosen family. - You need audio or video references.
- You need more than 10 seconds.
- You must reproduce a look and can't have the family change.
What about the old Video 1.0 route?
The docs mark Video 1.0 as retiring soon, an alias for the same Auto pipe. New builds should call POST /v1/videos with sume/auto. Do not build on any trait of the output to guess the family; the docs say not to.
Sources
Related posts
More in Models
- Voice cloning API: clone once in the app, speak via the API
Sume has no API route that creates a voice clone. You clone once in the app, then send the voi_ id to the text to speech API on every call.
- Wan 3.0 1080p: how to request full HD from the API
Wan 3.0 outputs 480p, 720p or 1080p. Send resolution 1080p to wan-3.0 on POST /v1/videos, up to 30 seconds, with audio. See the request and the price.
- Wan 3.0 2-second clips: the shortest video length and what it costs
Wan 3.0's floor is 2 seconds, shorter than the 4-second minimum on Seedance 2.x models. Send duration 2 to wan-3.0; at 720p it costs $0.25 before the agent fee.
- Wan 3.0 30-second video: one clip, no stitching
Wan 3.0 makes a single clip of up to 30 seconds with audio. Set duration to 30 on wan-3.0 in POST /v1/videos. Here is the request, the cost, and the limits.
Written by Sume