Which Sume video models take 30 seconds: four ids in the catalog
Four ids in Sume's video catalog reach 30 seconds: seedance-2.5, wan-3.0, higgsfield-genjutsu and h3-max-recast. Which make a clip from a prompt.

Four catalog ids reach 30 seconds on Sume: seedance-2.5, wan-3.0, higgsfield-genjutsu and h3-max-recast. Only the first two generate a 30-second clip from a text prompt.
Each other model in the catalog tops out at 15 seconds, apart from Gemini Omni Flash 1.1 at 10.
The four
| Model id | Range | Needs |
|---|---|---|
| seedance-2.5 | 4 to 30 s | a prompt |
| wan-3.0 | 2 to 30 s | a prompt |
| higgsfield-genjutsu | 4 to 30 s | a source video plus 1 to 8 reference images |
| h3-max-recast | 5 to 30 s | a source video plus 1 to 4 person photos |
Two caveats
Pin a model for a 30-second clip rather than relying on sume/auto, which does not disclose which family serves the request.
higgsfield-genjutsuis in the catalog only when its provider is configured.- For the last two, the duration equals the source video length, rounded up.
- Always call
GET /v1/videos/modelsfor the live list.
Prompt-driven versus source-driven
seedance-2.5 and wan-3.0 start from text, optionally with images. higgsfield-genjutsu is Motion Transfer: you provide one source video plus 1 to 8 reference images and it follows the source's motion. h3-max-recast replaces the people in a source video with up to 4 people from photos, keeping the motion, camera, cuts and sound.
Because the last two take their length from the source video, they are tools for existing footage, not for a new 30-second idea.
Price check
Prices differ by shape: at 720p, 30 seconds of Wan 3.0 is $3.75 and of Seedance 2.5 about $17.33 on Sume (list times 1.25). H3 Max Recast lists at $0.30 and $0.45 per second at 768p and 1080p before Sume's 1.25 factor.
Read the live catalog price for the two source-driven ids before you queue a long job.
- Check provider availability for genjutsu.
- Trim the source video before you submit.
- Use
GET /v1/videos/modelsfor the final word.
Sources
Related posts
More in Models
- Which AI video models take an audio file as a reference on Sume?
MiniMax H3 and H3 Max, Wan 3.0 and the Seedance 2.x rows accept audio references on Sume; Omni and Kling do not. H3 limits: 3 clips, 2-15 s each, 15 s total.
- Which Sume video models accept an audio reference (audio_url)?
Seedance 2.x, Wan 3.0, MiniMax H3 and H3 Max take audio and video references on Sume. Gemini Omni Flash 1.1 and Recast do not. Rates and limits.
- Which Sume video models take an audio_url reference, which do not
Sume video rows list supported_input_references per model. The docs show seedance-2 with audio_url, H3 Max with audio, and Gemini Omni Flash 1.1 without it.
- Which video models does Sume list in October 2026? Twelve ids
Sume's video catalog has twelve ids, from seedance-2.5 at 30 seconds to gemini-omni-flash-1.1 at 4K. Length and resolution for each; Veo 3.1 is not listed.
Written by Sume