1:1 square AI video on Sume: eight rows take it, Omni does not
Eight Sume video rows list 1:1 as an aspect ratio. Gemini Omni Flash 1.1 allows only 16:9 and 9:16. Cheapest square clip: 5 s at 480p is $0.31.

Eight video rows on Sume accept aspect_ratio: "1:1": the four Seedance rows (2.5, 2, 2-mini, 2-fast), Kling 3, Wan 3.0, MiniMax H3 and MiniMax H3 Max. Gemini Omni Flash 1.1 does not; it takes 16:9 or 9:16 only. The cheapest square clip is a 5-second 480p Wan 3.0, H3 or H3 Max job at 5 x $0.0625 = $0.3125, shown as $0.31.
Which rows list 1:1
The list below is from the Video Router capabilities. Some rows send no aspect ratio at all, because they follow the source media.
| Row | 1:1 | Other ratios listed |
|---|---|---|
| seedance-2.5, 2, 2-mini, 2-fast | yes | auto, adaptive, 21:9, 16:9, 4:3, 3:4, 9:16 |
| kling-3 | yes | 16:9, 9:16 |
| wan-3.0 | yes | auto, adaptive, 16:9, 4:3, 3:4, 9:16 |
| minimax-h3, minimax-h3-max | yes | adaptive, 21:9, 16:9, 4:3, 3:4, 9:16 |
| gemini-omni-flash-1.1 | no | 16:9, 9:16 |
| grok-imagine-video-1.5, h3-max-recast, higgsfield-genjutsu | not sent | output follows the source |
Price of a square clip
The ratio does not change the price. Sume prices video by output second and resolution, so a 1:1 clip costs the same as 16:9 at the same length and tier. At 5 seconds: Wan 3.0 or H3 at 480p is $0.3125; Seedance 2 at 480p is 5 x $0.17577 = $0.87885, shown as $0.88; Seedance 2.5 at 480p is 5 x $0.268677 = $1.343385, shown as $1.34.
- Kling 3 lists 720p and 1080p only, and 4 to 15 seconds.
- The 4:3 ratio and 21:9 are not on every row; Wan has no 21:9.
- The docs say
sizeis rejected on every v1 model, so useresolutionplusaspect_ratio.
If you only have Omni
Omni's native audio and 4K tier make it attractive, but its ratio list ends at 16:9 and 9:16. To publish a square clip from an Omni render you would crop a vertical or wide file. A 9:16 clip cropped to 1:1 keeps the full width and loses height, so frame subjects near the centre if you plan to do that. Otherwise pick one of the eight rows above and ask for 1:1 directly.
Checking the live list
Rows change as providers are added or retired, so confirm with GET /v1/videos/models and read supported_aspect_ratios for the row you plan to use. Do not rely on a copy of this table in production code.
If a row reports 1:1 and the request still fails, check that the ratio is valid together with the resolution and duration you chose. The error body names the field.
Sources
Related posts
More in Models
- Edit a video with Gemini Omni Flash on Sume: fields allowed or refused
Omni Flash 1.1 edit mode on Sume takes one video_url plus a prompt, defaults to 720p, and refuses aspect_ratio, duration and other media fields.
- Omni Flash 1.1 is billed in tokens: 5,792 per 720p second, in dollars
Google bills Gemini Omni Flash 1.1 at 5,792 output tokens per 720p second and $17.50 per million. The math to dollars, and the Sume per-second rate.
- Omni Flash 1.1 takes no audio reference: where a Short's voice goes
Gemini Omni Flash 1.1 accepts image and video references but not audio_url. For a voiced Short use native audio or a Timeline spine; 60 s is $7.60 at 720p.
- Gemini Omni Flash references on Sume: 10 images, 3 videos of 3 s
Omni Flash 1.1 on Sume takes up to 10 reference images and 3 reference videos of at most 3 s each, so 9 s of video. No audio reference. Tags and costs.
Written by Sume