HappyHorse video-edit ids and the Sume edit route

Alibaba Model Studio lists happyhorse-1.1-t2v, -i2v (first frame) and -r2v (reference), and recommends editing on happyhorse-1.0-video-edit or wan2.7-videoedit rather than on 1.1. Sume does not carry any HappyHorse id; its video-edit route is gemini-omni-flash-1.1 with a video_url.

What Model Studio lists

The page describes the 1.1 generation ids as supporting 480P, 720P and 1080P output at 3-15 seconds, 24 fps, MP4. For edits it points to two other ids, so a request to edit an existing clip should not be sent to the 1.1 generation ids.

The Sume edit route

Sume's Video Router documents gemini-omni-flash-1.1 as one catalog id that is routed by the shape of the request. Sending a video_url selects video-to-video edit: the prompt describes the change, resolution is optional and defaults to 720p, and aspect_ratio and duration are not sent. video_url is the edit source, not a reference, so it cannot be combined with image_url, end_image_url or reference_*_urls.

Native audio is always on for this model, and billing is provider list times 1.25 per output second by resolution. Check GET /v1/video-router/models for current capabilities rather than assuming them.

curl -X POST https://api.sume.com/v1/video-router/generate \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: video-router-edit-001" \
  -d '{
    "model": "gemini-omni-flash-1.1",
    "prompt": "Replace the bottle with an apple. Keep everything else the same.",
    "video_url": "https://example.com/clip.mp4",
    "resolution": "720p",
    "mode": "async"
  }'

Choosing between them

If you need HappyHorse itself, call Alibaba Model Studio and use its edit ids. If you need an edit inside the Sume catalog, use the route above; it is a different model, so the result will not match a HappyHorse edit frame for frame. Test on one short clip before you migrate a pipeline.