2-second logo sting from Omni: generate 3 s, trim, $0.395 at 720p
Gemini Omni Flash 1.1 outputs 3 to 10 seconds. A 2-second sting on Sume is a 3-second clip at $0.375 (720p) plus a $0.02 video trim.

Generate 3 seconds and trim to 2. Gemini Omni Flash 1.1 outputs 3 to 10 seconds per clip, so a 2-second logo sting cannot be requested directly. On Sume a 3-second 720p clip is $0.375 and a video trim is $0.02 per job, which is $0.395 for the sting.
The two jobs
First submit gemini-omni-flash-1.1 with duration: 3 and the 720p resolution. Native audio is always on. Then call POST /v1/video-trim on the result with start and either end or duration; it returns a new MP4 with only that range.
Trim needs a workspace-hosted clip, so use the finished artifact, and send an Idempotency-Key on both calls.
| Resolution | 3 s Omni clip | Trim | Total |
|---|---|---|---|
| 360p | $0.1125 | $0.02 | $0.13 |
| 720p | $0.375 | $0.02 | $0.395 |
| 1080p | $0.5625 | $0.02 | $0.58 |
| 4K | $1.125 | $0.02 | $1.145 |
Which second to keep
Cut from the end, not the start. A logo reveal tends to resolve in the last second, so keep the range that holds the settled mark, and have the prompt put the mark on screen within the first 2 seconds.
Because sound is always on, check what the clip sounds like before you place it in an edit. If you do not want it, cover it with a soundtrack on a Timeline.
When 3 seconds is fine
If your slot is 2.5 or 3 seconds, skip the trim. The three-second floor is also the shortest Omni clip, which suits a bumper better than a 2-second logo.
Rates are the Sume card on 2026-10-07. Read pricing_skus from GET /v1/videos/models and the catalog for the live trim price.
Sources
Related posts
More in Media tools
- A 45-second dance reference needs two Kling motion control jobs: $7.09
Sume's Kling 3.0 motion control caps one reference at 30 seconds. A 45-second dance is a 30 s plus a 15 s job, about $7.09, joined by a timeline.
- Audio detach size for a 180 s Short: 34.56 MB wav, 2.88 MB mp3
The byte arithmetic for a 3-minute track from audio detach: stereo 48 kHz wav, mono 16 kHz wav and 128 kbps mp3, with the fields that set each size.
- Can Gemini Omni edit change a video's aspect ratio? No
On Sume, Omni's edit mode takes a video_url and a prompt, defaults to 720p and accepts no aspect_ratio or duration. A 16:9 source stays 16:9, so plan the crop.
- Caption a talking-head video: style, placement and phrasing
Caption a talking-head clip with the Sume API: pick a style, move the line off the face, set words per card. One request, $0.20 for up to 60 seconds.
Written by Sume