Kling 4.0 Flash 3-second minimum vs Sume's 4-second kling-3 floor
Kling 4.0 Flash starts at 3 seconds. Sume's kling-3 starts at 4. The models that can render a 3-second clip on Sume, and what a 3 s request costs.

fal's Kling 4.0 explainer lists 3 seconds as the shortest clip for both Kling 4.0 and Kling 4.0 Flash. Sume's kling-3 starts at 4 seconds, so a 3-second request to it is outside its range. On Sume, a 3-second clip comes from wan-3.0 (from 2 seconds) or gemini-omni-flash-1.1 (from 3 seconds).
Minimum duration by model
The figures come from the Sume video catalog and docs.
| Model | Minimum seconds | Maximum seconds |
|---|---|---|
| wan-3.0 | 2 | 30 |
| gemini-omni-flash-1.1 | 3 | 10 |
| kling-3 | 4 | 15 |
| seedance-2.5 | 4 | 30 |
| seedance-2, 2-fast, 2-mini | 4 | 15 |
| grok-imagine-video-1.5 | 4 | 15 |
| minimax-h3, minimax-h3-max | 5 | 15 |
What a 3-second clip costs
Using the provider list, times 1.25, rounded up to the cent per job:
| Model and tier | List per second | Sume price for 3 s |
|---|---|---|
| wan-3.0 at 480p | $0.05 | $0.19 |
| wan-3.0 at 1080p | $0.20 | $0.75 |
| gemini-omni-flash-1.1 at 720p | $0.10 | $0.38 |
| gemini-omni-flash-1.1 at 4K | $0.30 | $1.13 |
Submit a 3-second request
Wan 3.0 is the cheapest at 480p. Because the minimum is model-specific, check supported_durations first.
curl -X POST "https://api.sume.com/v1/videos" \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-omni-flash-1.1",
"prompt": "A match strikes and lights a candle",
"duration": 3,
"resolution": "720p",
"aspect_ratio": "16:9"
}'If you wait for Kling 4.0
Kling 4.0 Flash is early access and no API is published in the sources I read. A 3-second loop that works today on Omni or Wan keeps working when Kling arrives, so there is no reason to block on it.
Sources
Related posts
More in Models
- Kling 4.0 Flash is first-frame only; what Sume's Kling 3 accepts
Kling 4.0 Flash early access takes a first-frame image, 20 s, 720p, SDR. Sume ships kling-3: 4 to 15 s, 720p/1080p, priced per second. Limits side by side.
- Kling 4.0 Flash is 720p only: Sume models that reach 1080p and 4K
Kling 4.0 Flash early access outputs 720p, 3 to 20 seconds. If you need 1080p or 4K today, these Sume models take those resolutions, with the exact prices.
- Kling 4.0 Omni Reference takes 15 references; Sume limits compared
fal says Kling 4.0 Omni Reference accepts up to 15 references. On Sume, kling-3 takes none; Wan 3.0 and Gemini Omni Flash 1.1 publish their own limits.
- Lip sync with a hand over the mouth: sync-3 vs Fabric on Sume
Sync Labs says sync-3 handles obstructions on faces. Sume's lip-sync routes start from a still plus audio. What each takes as input and what is promised.
Written by Sume