Kling 4.0 Flash is available on EmpirioLabs. It is the faster, lower-cost model in Kuaishou's Kling 4.0 family, whose API opened on November 4, 2026. One request makes a clip of 3 to 20 seconds at 720p with native audio, and the inputs you attach decide what it does: a prompt alone, a first frame, reference images and videos, or a video to edit.
How it compares
| Kling 4.0 Flash | Kling 4.0 | |
|---|---|---|
| Resolutions | 720p | 720p, 1080p |
| Clip length | 3 to 20 seconds | 3 to 30 seconds |
| Frames | First frame | First, middle and last frames |
| Reference images and videos | Yes | Yes |
| Video editing | Yes | Yes |
| Native audio | Yes | Yes |
What the model does
Text to video. A prompt of up to 26,000 English characters, at 16:9, 9:16, 1:1 or 21:9.
First frame. Send one image as image and the clip starts on it, following its aspect ratio.
References. Up to 10 images for characters, objects, scenes or style (reference_images), and reference videos for motion, camera work or style (reference_videos). Refer to them in the prompt as @image_1, @image_2 and @video_1.
Video editing. Send a clip of 3 to 20 seconds as video with an instruction in the prompt. The result keeps the clip's length.
How to call Kling 4.0 Flash
Video generation is asynchronous: submit the job, then poll it. Set model to kling-4-0-flash:
curl -X POST https://api.empiriolabs.ai/v1/videos/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kling-4-0-flash",
"prompt": "A red kite climbs over a windy beach at sunrise, a child running below, wide tracking shot.",
"duration": 5
}'
# {"job_id": "...", "status": "processing", "poll_url": "/v1/jobs/..."}
curl https://api.empiriolabs.ai/v1/jobs/JOB_ID \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY"
The finished job returns a signed video URL, the clip's length, and the usage it was billed for. To animate a picture instead, add "image": "https://..."; to edit a clip, send "video": "https://..." and describe the change.
Operational notes
- Output is 720p. The default length is 5 seconds; a video edit ignores
durationand returns the length of the clip it edits. - Input videos must be 3 to 20 seconds each, 20 seconds in total, and 700 to 4553 pixels on each side. Images need at least 300 pixels and an aspect ratio between 2:5 and 5:2.
- Any video input, whether a clip to edit or a reference video, is billed at the video input rate on at least twice the length of the output. The job result reports the billed seconds.
- In the Playground, one attached image becomes the first frame, and two or more are used as references. Over the API, the field you put each file in sets its role.
- For last or middle frames, or 1080p, use Kling 4.0.
Pricing
Kling 4.0 Flash is pay as you go, billed per second, with a separate rate for requests that include a video. Current rates are on the model page and the pricing page.
Try it
Run it in the Playground with no code, or read the API reference for every parameter.




