HappyHorse 1.1 API ids: 480P to 1080P, 3 to 15 seconds
Alibaba lists happyhorse-1.1-t2v, -i2v and -r2v at 480P, 720P or 1080P for 3 to 15 seconds. Sume's catalog docs name HappyHorse 1.1 as not in the v1 catalog.

Alibaba Cloud Model Studio lists three HappyHorse 1.1 model ids: happyhorse-1.1-t2v, happyhorse-1.1-i2v and happyhorse-1.1-r2v. Each outputs 480P, 720P or 1080P, 3 to 15 seconds, 24 fps MP4, with audio. Sume's catalog docs name HappyHorse 1.1 as outside the v1 catalog, so you cannot call it by id on Sume.
Model ids are from Alibaba's video generation page; the Sume side is from the Video router docs and the repository's API notes, read 2026-10-01.
What are the HappyHorse ids and limits?
The 1.1 family adds a 480P tier. The 1.0 ids on the same page start at 720P, and the 1.0 family also has a video-edit id.
| Model id | Type | Output |
|---|---|---|
happyhorse-1.1-t2v | Text-to-video | 480P, 720P, 1080P; 3-15s; 24 fps |
happyhorse-1.1-i2v | First-frame image-to-video | 480P, 720P, 1080P; 3-15s; 24 fps |
happyhorse-1.1-r2v | Reference image-to-video | 480P, 720P, 1080P; 3-15s; 24 fps |
happyhorse-1.0-t2v | Text-to-video | 720P, 1080P; 3-15s; 24 fps |
happyhorse-1.0-video-edit | Video editing | 720P, 1080P; 3-15s; 24 fps |
Can I call HappyHorse 1.1 on Sume?
Not at the time I read the docs. The API notes list Happy Horse 1.1 among families that are not in the v1 catalog. Ids not listed in GET /v1/video-router/models are rejected on generate, so read that endpoint rather than assuming an id.
What can I use instead?
Send model: "sume/auto" and Sume picks the family; the response echoes sume/auto and does not disclose which family ran. Or pin a listed id such as seedance-2.5 or gemini-omni-flash-1.1. Compare the 1.0 case in HappyHorse 1.0 vs Sume catalog ids.
What should I check before switching ids?
Read supported_resolutions, supported_durations and supported_aspect_ratios from the models endpoint for the id you pick; each model advertises its own subset, so a 480P tier or a 15 second clip is not a given.
Sources
Related posts
More in Models
- Hedra Character 3 aspect ratios vs Sume Avatar Video ratios
Hedra Character 3 lists seven aspect ratios including 9:21 and 21:9. Sume Avatar Video supports five: 1:1, 3:4, 9:16, 4:3 and 16:9, default 9:16.
- HeyGen cinematic avatar API: 3 looks per shot vs Sume's one
HeyGen cinematic_avatar takes a prompt and 1-3 avatar looks with no script. Sume Avatar Video resolves one avatar per final video from a script.
- Ideogram 4 custom_model_uri vs Sume catalog ids and sume/auto
Ideogram's custom-model endpoint picks a private model by custom_model_uri. Sume has no such field: you choose a catalog id or sume/auto. What to send instead.
- Ideogram 8K output resolution API vs Sume 512 to 4K tiers
Ideogram 4.0 takes output_resolution 1k, 2k, 4k or 8k as a pixel budget. Sume's image route takes a normalized 512, 1K, 2K or 4K tier.
Written by Sume