Mixer AI
Kling 4.0 Flash
A lighter Kling 4.0: clips of 3–20 seconds in 720p from text and references, or from a start frame.
When to choose it
Kling 4.0 Flash is the short, 720p version of Kling 4.0. It has two modes: Text and references builds a scene from a prompt, up to 7 photos and 5 videos; Start frame brings one photo to life. Choose it when 720p and 20 seconds are enough; for 1080p, 30 seconds and a chain of keyframes there is Kling 4.0.
- Up to 7 photos and 5 videos in one request; the videos together up to 20 seconds.
- Start frame: one optional photo sets the composition and format.
- Aspect ratios Auto, 16:9, 9:16, 1:1 and 21:9 in references mode.
Modes and settings
- Text and references: a prompt up to 8000 characters, up to 7 photos and up to 5 videos totaling up to 20 seconds; the Video sound switch keeps the sound of reference videos.
- Start frame: one optional photo; without it choose 16:9, 9:16, 1:1 or 21:9, with it the format follows the photo.
- Duration 3–20 seconds, 720p only; 1, 2 or 4 results per run.
- Billing is per second. With a reference video you pay for the result seconds plus the larger of two values: the input video length or the result length.
Price in coins
| Quality / size | Input | Coins / second |
|---|---|---|
| 720p | First frame | — |
| 720p | Text and references | — |
| 720p | With video reference | — |
Billing is per second, not per fixed-length clip. The rate is multiplied by the billable duration; the complete request total is rounded up to a whole coin once.
With a reference video you pay for the result seconds plus the larger of two values: the input video length or the result length, at the With video reference rate. The minimum is 3 seconds.
≈ marks a fractional rate rounded to two decimal places for display; billing uses full precision.
The dollar price follows the current coin rate.
What you can make
- Quick tries of a scene before running it in full Kling 4.0.
- A short clip from one photo: set a start frame and describe the motion.
How to direct the result
- Say what each reference is for: hero, location or object.
- In Start frame mode describe only the motion and the camera: the look is already set by the photo.
Example: one photo comes alive
Start frame: a woman at a bus stop in the rain, medium shot. She checks her watch, then looks down the street as a bus arrives from the right. Static camera, a slow push-in at the end. Her face and coat stay the same. Soft overcast light.
What to keep in mind
- Flash gives 720p and up to 20 seconds only; choose Kling 4.0 for 1080p and 30 seconds.
- Start frame mode accepts no video: videos belong to references mode only.
Sources
Guides and comparisons using this model
FAQ
How is Flash different from Kling 4.0?
Flash makes clips of 3–20 seconds in 720p only and builds no chain of keyframes. Kling 4.0 goes up to 30 seconds, offers 1080p and keyframes with middle frames.
How many photos and videos can I attach?
In Text and references mode, up to 7 photos and 5 videos. The videos together must not exceed 20 seconds.
How is a clip with a reference video billed?
You pay for the result seconds plus the larger of two values: the input video length or the result length, at the With video reference rate.
What is the minimum duration?
3 seconds; it is also the minimum billable time.
Can I keep the sound of my uploaded video?
Yes. In references mode switch on Video sound.
Which aspect ratios are available?
In references mode: Auto, 16:9, 9:16, 1:1 and 21:9. In Start frame mode a photo sets the format; without a photo choose 16:9, 9:16, 1:1 or 21:9.
What changes the price?
The coin rate per second depends on quality, mode and, for some models, sound. Multiply it by the billable duration. Where input video is charged, its duration also counts. The complete request total is rounded once.
Do I need a separate model subscription?
No. In Mixer AI, you top up one coin balance and use it for the tasks you need. You do not need a separate subscription to this model.