Kling 3 duration and aspect ratio limits: Kling's own vs Sume's
Kling's own map lists 3 to 15 seconds for Kling 3.0; Sume's kling-3 takes 4 to 15 seconds at 16:9, 9:16 or 1:1. Values outside the list are refused.
Kling 3.0 makes 3 to 15 second clips according to Kling's own capability map; on Sume, kling-3 accepts 4 to 15 whole seconds and the aspect ratios 16:9, 9:16 and 1:1. A duration or aspect_ratio outside those lists is refused with an unsupported_capability error that names the supported values, rather than being rounded.
Sume limits are read from the Video generation docs and catalog code; Kling's from its capability map, read 2026-09-29.
What are the limits side by side?
| Item | Kling's own (Kling 3.0) | Sume `kling-3` |
|---|---|---|
| Duration | 3 to 15 s | 4 to 15 s |
| Resolution | 720P, 1080P, 4K | 720p, 1080p listed |
| Aspect ratios | Not on the map | 16:9, 9:16, 1:1 |
| Audio | Native audio | Optional, default on |
| Reference inputs | Element control | None |
| Frames | First/last frame | first_frame, last_frame |
How do I ask for a valid clip?
List GET /v1/videos/models and read supported_durations and supported_aspect_ratios for kling-3; both come back as arrays. Then send values from those arrays.
curl "https://api.sume.com/v1/videos/models" \
-H "Authorization: Bearer $SUME_API_KEY" \
| jq '.data[] | select(.id=="kling-3") | {supported_durations, supported_aspect_ratios}'Does aspect_ratio always apply?
No. In current code it is passed to the model for text-to-video only. With a first frame the output follows that image, so crop the image to 9:16 or 1:1 first.
What if I need a 3-second clip or a longer one?
Three seconds is below kling-3's floor on Sume. Wan 3.0 starts at 2 seconds and Gemini Omni Flash 1.1 at 3; seedance-2.5 and wan-3.0 reach 30. See AI video length limits by model.
Sources
Related posts
More in Models
- Kling 3 first and last frame API: request, limits and a gotcha
On Sume, kling-3 takes a first and optional last frame via frame_images, for 4-15 seconds. Send frame one in the shape you want; aspect_ratio is text-only.
- Kling 3 lip sync with your own audio: what each API does
Kling lists lip sync driven by text or audio. Sume's kling-3 takes no audio input, only a generate_audio switch; models with audio references are listed.
- Kling 3 native audio: what the on and off price difference is
On Sume, kling-3 costs $0.14 a second silent and $0.21 with audio. Audio is on unless you send generate_audio false, so the default is the higher price.
- Lyria 3 Pro or Lyria 3.5: which model id do I send?
Sume's Music Router accepts sume/music-auto, lyria-3.5 and lyria-3-pro. What each id does, how to pin one, and what Google lists for the models.
Written by Sume