Gemini Omni extend video: Google's 40 s cap vs Sume's modes
Google's Gemini Omni can extend a video by 3-10 s up to 40 s. Sume's Omni row has no extend mode; here is what it offers instead.

Google's Gemini Omni can extend an existing video, but Sume's gemini-omni-flash-1.1 row has no extend mode. It routes four request shapes: text to video, image to video, reference to video and video edit. To go longer on Sume you chain clips yourself.
Google's behavior is from its Omni page and changelog; Sume's from the Video Router docs and catalog code, all read 2026-09-30.
What does Google's video extension do?
The Omni page says the model analyzes the input video to generate a 3 to 10 second continuation. Uploaded input videos must be 10 seconds or less, and the total extended length is capped at 40 seconds. The August 27, 2026 changelog lists "Video extension" among the features that arrived with general availability of gemini-omni-1.1-flash.
What does Sume's Omni row support instead?
| Capability | You send | Limit in the docs |
|---|---|---|
text_to_video | prompt | 3 to 10 s per request |
image_to_video | image_url (+ optional end_image_url) | 3 to 10 s per request |
reference_to_video | reference_image_urls and/or reference_video_urls | Up to 3 reference clips, each up to 3 s |
video_to_video (edit) | video_url | Prompt describes the edit; no duration |
Can a reference video stand in for extension?
Only loosely. reference_video_urls accepts up to 3 clips of at most 3 seconds each, and they guide the new clip rather than continuing the source. The edit mode changes an existing video and takes no duration, so it does not add length either.
How do I make a longer video on Sume?
Two documented routes. Chain clips: generate one clip, take its last frame, and send it as image_url on the next request; see Veo 3.1 extend vs chaining clips for the pattern. Or pick a model with a longer envelope: the docs say seedance-2.5 accepts 4 to 30 seconds. Chaining is your own loop, so continuity between clips is not guaranteed by the API.
Sources
Related posts
More in Models
- Gemini Omni reference video length: 3 seconds per clip on Sume
On Sume, each Gemini Omni Flash reference video can be at most 3 seconds, with up to 3 clips. Trim longer footage first, then address clips as VIDEO_REF tags.
- Gemini TTS API: which engine Sume's TTS routes to
Gemini 3.8 TTS is not in Sume's TTS Router, which lists Cartesia Sonic ids only. What Sume's TTS takes for voice, engine and length, with a checklist.
- Generative Extend any aspect ratio: Sume video ratios
Premiere's Generative Extend now takes any aspect ratio. Sume's gemini-omni-flash-1.1 makes 16:9 or 9:16 clips; for other shapes, conform with Timeline fit.
- Genjutsu Object Swap API: Sume serves Motion Transfer only
Higgsfield pairs Motion Transfer with Object Swap in Genjutsu. Sume's Genjutsu row serves Motion Transfer only; Object Swap is rejected by name.
Written by Sume