Gemini Omni Flash 9:16: two ratios only, and a vertical ad check
On Sume, gemini-omni-flash-1.1 accepts 16:9 and 9:16 only, 3-10 s with audio always on. Ratio table across Sume video models.

Yes, Gemini Omni Flash makes vertical video on Sume, and 9:16 is one of only two ratios it accepts, along with 16:9. gemini-omni-flash-1.1 generates 3 to 10 seconds per job, always with audio, and lists 360p, 720p, 1080p and 4K. It does not accept 1:1 or 4:5. If your feed placement needs a square or 4:5 frame, pick another model or crop afterward.
Hedra's model comparison (read 2026-10-02) lists Gemini Omni Flash at $6.00 per minute at 1080p and an Elo of 1,240; Sume's own billing is per second and is shown below.
Which Sume models take which ratios?
Ratios differ by model, so check before you build the template. The table is from the Sume catalog.
| Model | Ratios |
|---|---|
| gemini-omni-flash-1.1 | 16:9, 9:16 |
| kling-3 | 16:9, 9:16, 1:1 |
| seedance-2.5 | auto, adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
| grok-imagine-video-1.5 | No aspect_ratio field; follows the input image |
What do I check before a vertical ad ships?
Open the finished file and read its dimensions, not the request. Then check the safe area: platform interfaces cover the top and bottom of a vertical frame, so keep faces and text away from the edges. Sume's video-frames tool can pull stills from the clip so you can inspect those regions without playing the whole video.
Does the always-on audio matter?
Yes. You cannot turn audio off on this model. If you plan to replace the sound with a voiceover or music bed, join the clip in the timeline and set the soundtrack there, or choose a model with audio on or off such as kling-3.
Sources
Related posts
More in Models
- Gemini Omni with several videos: 3 references, no cross-video use
Gemini Omni takes up to 3 reference clips of 3 s each, yet Google warns that reasoning across several videos may degrade output. Sume: one video_url source.
- Gemini Omni REST: output_video is SDK-only, read the steps array
Calling Gemini Omni over REST? interaction.output_video is SDK-only. Read the base64 video from the model_output step; on Sume you get a media URL instead.
- Gemini Omni [# Sources] and [# References] tags vs Sume fields
Gemini Omni binds media to roles with tags like <FIRST_FRAME> and [# Sources ...]. Sume uses request fields instead: image_url, end_image_url, reference lists.
- Gemini Omni and Veo in Korean: only English is fully supported
Google's Omni and Veo pages say English is fully supported; other languages aren't evaluated. For Korean prompts, describe in English and quote on-screen text.
Written by Sume