Kling 3.0 square video API: can I request 1:1 on Sume?
Yes: Sume's kling-3 row lists 16:9, 9:16 and 1:1 at 720p or 1080p, 4 to 15 s, with an audio-on rate. What it refuses, what it costs, and a request body.
Yes. The kling-3 row in Sume's Video Router catalog, named Kling Video v3 Pro, lists three aspect ratios: 16:9, 9:16 and 1:1. It takes 720p or 1080p, durations of 4 to 15 seconds, text-to-video and first-and-last-frame image-to-video, and it does not take reference images, videos or audio. That is from the Video Router docs and the live catalog at GET /v1/videos/models.
Square is the ratio people ask about because feed placements still use it, and not every row offers it. The table shows where 1:1 is and is not available.
Which Sume video rows offer 1:1, and which do not?
Sume validates against the catalog, so an aspect ratio a model does not advertise is a 400, not a silent crop. Gemini Omni Flash 1.1 is the notable gap: it is 16:9 or 9:16 only.
| Row | Aspect ratios |
|---|---|
Kling Video v3 Pro (kling-3) | 16:9, 9:16, 1:1 |
Gemini Omni Flash 1.1 (gemini-omni-flash-1.1) | 16:9, 9:16 |
| MiniMax H3 / H3 Max | adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
| Wan 3.0 | auto, adaptive, 16:9, 4:3, 1:1, 3:4, 9:16 |
| Seedance 2.5 and 2.0 family | auto, adaptive, 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
What does a square Kling clip cost?
Kling's catalog row carries one per-second rate pair, audio off and audio on. The provider list is $0.112 and $0.168 per second; with the 1.25 margin Sume bills $0.14 and $0.21 per second. A 5-second square clip with audio off is $0.70 and with audio on $1.05; a 10-second one is $1.40 and $2.10. Audio is the lever, so read the related post on audio cost before pinning it.
What does the request look like?
On /v1/videos, send the model id, a prompt, aspect_ratio: "1:1" and a resolution. Keep it to text or frame images; a input_references array on Kling is a 400.
Sume's catalog does not expose size, so a pixel size such as 1080x1080 is refused; use resolution plus aspect_ratio instead.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"kling-3","prompt":"A ceramic mug turning on a wooden table, soft window light","aspect_ratio":"1:1","resolution":"720p","duration":5}'When is a different row the better pick for square?
If you need reference images, or a 30-second square, Kling cannot do it: no references and a 15-second ceiling. Seedance 2.5 and Wan 3.0 both list 1:1 and reach 30 seconds. If you need 4K, only Gemini Omni Flash 1.1 offers it, and only in 16:9 or 9:16, so crop to square afterwards with Sume's video tools.
Sources
Related posts
More in Models
- Kling 3.0 subject binding limits and what Sume kling-3 takes
Kling's subject binding takes up to 4 images, a 3-8 s clip and a voice sample. Sume's kling-3 takes none of them, so lock identity with a first frame.
- Kling 3.0 in the Sume Videos panel: 5-15 s choices vs API 4-15 s
The panel offers Kling 3.0 at 5, 6, 8, 10 or 15 seconds and no end frame. The API accepts any whole second from 4 to 15 and a last frame.
- Kling 4.0 takes 15 reference assets; what Sume models accept
Kling's page lists up to 15 combined references for Kling 4.0. On Sume the cap is per model: Wan 10/5/5, H3 9/3/3 (12 total), Omni 10 images and 3 short videos.
- Kling 3.0 starts at 3 seconds; Sume's kling-3 starts at 4
Kling's own page lists 3-15 seconds for Kling 3.0. The kling-3 id on Sume accepts 4-15, so a 3 second request returns unsupported_capability.
Written by Sume