Video models
Kling 3.0
On this page
Cinematic text & image to video with native sound and multi-shot support.
| modelId | kling-3-0 |
| Modality | video |
| Pricing | See this model on the Pricing page for the current per-call price (with your markup). |
Operations
| Operation | modelId | Endpoint | Required input |
|---|---|---|---|
| Default | kling-3-0 | POST /api/v1/generate | multi_shots, prompt, duration |
| Poll task | — | GET /api/v1/task/{id}?model=kling-3-0 | — |
Input parameters
| Field | Type | Required | Values / example |
|---|---|---|---|
| image_urls | string[] | No | Start Frame / End Frame |
| multi_shots | boolean | Yes | True/false (default: false) |
| multi_prompt | object[] | No | Up to 5 shots, each 1-12 seconds. Their durations must add up to Duration. (array of { prompt, duration }) |
| sound | boolean | No | True/false (default: true) |
| prompt | string | Yes | Text value Max 2500 characters. (default: A barista pours latte art in slow motion at a cozy window counter, morning light, steam curling.) |
| duration | number | Yes | Range 1-15 (default: 5) |
| kling_elements | object[] | No | Array of { name, description, media } |
| aspect_ratio | string | No | Options: 1:1 | 9:16 | 16:9 (default: 1:1) |
| mode | string | No | Generation mode. std has standard resolution, pro has higher resolution. (options: std | pro | 4K) (default: std) |
Example request
bash
curl -X POST https://you.bot/api/v1/generate \
-H "Authorization: Bearer $YOUBOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{"modelId":"kling-3-0","input":{"image_urls":["https://example.com/input.jpg"],"multi_shots":false,"sound":true,"prompt":"A cinematic aerial shot of a coastal town at golden hour, gentle waves rolling onto the shore, warm light, slow camera push-in.","duration":5,"aspect_ratio":"1:1","mode":"std"}}'