Prompt
Text · Required
Loading the current model…
We could not open this model.
Return to the catalogue and choose an available model.
Back to the catalogue
- Kuaishou
- Standard
- Generate video
Kling 3
Direct multi-shot cinematic stories with native sound and stronger continuity.
Compare Kling 3 settings and cost estimates. Prompt-directed scenes with flexible 3–15-second duration and optional generated audio, using text or a first frame.
- Generate video
Kling 3 pricing example
$0.2822 Estimated per run
- Aspect ratio: 16:9
- Duration: 3
- With audio: false
Estimate checked . This example uses the configuration shown above. Inputs and settings can change the price; check the estimate for your own run before generating. Project storage is billed separately.
How AI usage and project pricing work →Curated output references.
What goes in. What comes back.
The model defines every slot it reads and every result it returns. Required inputs must be present before a run can begin.
Prompts and source material
Negative prompt
Text · Optional
First frame
Image and Video · Optional
Last frame
Image and Video · Optional
Files and structured results
Video
Video
Configure the run.
| Control | Available values | Requirement |
|---|---|---|
| Aspect ratio | 16:9, 9:16, and 1:1 | Optional |
| Duration | 3–15 | Optional |
| With audio | On, Off | Optional |
Works especially well for
- Prompt-directed scenes with flexible 3–15-second duration and optional audio, using text or a first frame.
Know the trade-offs
- The app does not expose a structured multi-shot editor or last-frame input for this row. Describe a manageable shot rather than assuming every vendor storyboard control is available.
Continue from the result
Use it inside a production
- Suggested exercise: plan a ten-second chair reveal with a clear opening, one camera move, and a settled ending; inspect the chair's proportions across the clip. →
- Compare Kling 3 Turbo for iteration on a first-frame shot; choose a model with a final-frame input when the exact ending composition matters. →
Compare similar models
Compare models for the same capability. Check their inputs, output settings, and estimate using the same brief.
Configure the model.
Keep the result in the cut.
The generation returns to the scene, asset folder and timeline it belongs to.