Max AI video length: Runway Gen-4.5 10 s vs Sume's 30-second rows
Runway's Gen-4.5 runs 2 to 10 seconds and Omni 3 to 10. Sume's Wan 3.0 and Seedance 2.5 reach 30. Longest single clip by model, with the sources.

Runway's changelog lists Gen-4.5 at 2 to 10 seconds and Gemini Omni Flash at 3 to 10 seconds (Runway changelog, read 2026-10-09). Sume's docs give wan-3.0 2 to 30 seconds and seedance-2.5 4 to 30 seconds, while its Omni row stays at 3 to 10. For a one-take clip over 10 seconds you need a model with a longer ceiling.
What is the longest clip per model?
Sume lengths are from the video generation docs. They also say each other catalog model has a maximum of 15 seconds, and GET /v1/videos/models reports the live supported_durations.
| Model | Where | Length |
|---|---|---|
| Gen-4.5 | Runway API | 2 to 10 seconds |
| Gemini Omni Flash | Runway API | 3 to 10 seconds |
| Aleph 2.0 (edit) | Runway API | 2 to 30 seconds |
| gemini-omni-flash-1.1 | Sume | 3 to 10 seconds |
| wan-3.0 | Sume | 2 to 30 seconds |
| seedance-2.5 | Sume | 4 to 30 seconds |
| minimax-h3 | Sume | 5 to 15 seconds |
What does a long clip cost?
Length is not free. Omni on Sume is $0.125 a second at 720p, so 10 seconds is $1.25. Wan 3.0 and Seedance 2.5 have their own rates, so read the price for your resolution in the docs before you submit; Sume reserves the provider list times 1.25 per output second at submit.
When should you stitch instead?
Sume joins clips on its timeline; the docs treat the clip sequence and audio as Timeline 1.0 work.
- You need cuts: three 10-second Omni clips with different shots read better than one long take.
- You need 4K: Omni lists 4K and stops at 10 seconds, so build a longer 4K sequence from 10-second clips.
- You need to repair a middle section: re-render one clip, not the whole minute.
Sources
Related posts
More in Comparisons
- YouTube AI label: three auto-detection signals and Sume outputs
YouTube may label video automatically for its GenAI tools, C2PA metadata or internal detection. Sume docs do not mention C2PA, so here is what to check.
- Which audiobook stores accept AI narration? ACX, Apple, KDP, Spotify
ACX bans unauthorized AI narration, Apple narrates for you, KDP is an invite beta, Spotify wants a disclosure. Read 2026-10-10, plus where Sume TTS audio fits.
- Wan 2.7 custom audio (2-30 s) vs Sume Wan 3.0 audio references
Alibaba's Wan 2.7 takes a custom WAV or MP3 of 2-30 seconds. Sume's Wan 3.0 accepts up to 5 reference audio clips, 15 seconds in total, with an image or video.
- Auphonic audio cleanup vs Sume audio detach: different jobs
Auphonic cleans and levels audio; Sume audio detach only pulls the track out of a video as wav or mp3. Compare billing, limits and where each belongs.
Written by Sume