Text To Video And Image To Video
Kling 3.0 API generates video from a text prompt alone, or from a first frame image for precise composition control — both from one unified endpoint.
Kling 3.0 is Kling AI's video generation model with native audio and first/last frame control. Generate 3-15s clips at 720p, 1080p, or 4K.
| Specification | Credits | Price (USD) |
|---|---|---|
| Resolution4KGenerate AudioDisabled | 47.64 – 47.6667per second | $0.4764 – $0.4767per second |
| Resolution4KGenerate AudioEnabled | 47.64 – 47.6667per second | $0.4764 – $0.4767per second |
| Resolution720PGenerate AudioDisabled | 9.48 – 9.5per second | $0.0948 – $0.095per second |
| Resolution720PGenerate AudioEnabled | 14.28 – 14.3per second | $0.1428 – $0.143per second |
| Resolution1080PGenerate AudioDisabled | 12.72 – 12.7333per second | $0.1272 – $0.1273per second |
| Resolution1080PGenerate AudioEnabled | 19.08 – 19.1per second | $0.1908 – $0.191per second |
Prices follow the model configuration. Reference images are not billed unless the model says so.
Try Kling 3.0 online with a generation workspace, first and last frame control, and API-ready parameters. Generate 3-15s clips at 720p, 1080p, or 4K with optional native audio.

Kling 3.0 API generates video from a text prompt alone, or from a first frame image for precise composition control — both from one unified endpoint.
Pick 720p for fast drafts, 1080p for production quality, or 4K for ultra-high-resolution final output. Resolution is selectable per request.
Enable native audio to add synchronized sound effects to your video, or disable it for silent clips. At 4K, audio is included without extra cost.
Provide a start image and an optional end image and Kling 3.0 API generates smooth, coherent motion between them — precise control over composition and transitions.
Kling 3.0 generates synchronized sound effects aligned with the visuals, enabling immersive clips without a separate audio pipeline.
Kling 3.0 excels at rich lighting, texture, and detail. Generate up to 4K for brand films and high-end visuals that hold up at large sizes.
| Control | Type | Default | Notes | |
|---|---|---|---|---|
| 01 | prompt | text | — | — |
| 02 | image_url | image | — | — |
| 03 | aspect_ratio | string | 16:9 | — |
| 04 | video_length | string3 – 15 | 5 | — |
| 05 | resolution | string | 1080p | — |
| 06 | generate_audio | boolean | true | Whether to generate AI audio synchronized with the video. |
Start in the AI Playground to try Kling 3.0 without setup. Enter a prompt or upload first and last frames, pick resolution and duration, and preview results instantly.
Create an API key in the AI console to enable Kling 3.0 API access. Review the quick API docs to see required parameters and frame control inputs.
Submit a generation request with a prompt and optional image references. Poll the task status, receive the video output with optional native audio, and export your clips.
kling_3_0
POST to /api/openapi/submit with the model, a unique out_task_id, and parameters.
POST to /api/openapi/query with the same out_task_id until the task completes.
Save outputs in your own storage rather than hot-linking them.
Kling 3.0 is Kling AI's video generation model. It creates high-quality video from text or images, with native audio and cinematic control up to 15 seconds.
Yes. Kling 3.0 can generate native audio synchronized with the visuals. Audio is optional and can be toggled per request; at 4K it is included without extra cost.
Yes. Provide a first frame via image_url and an optional last frame via end_image_url, and Kling 3.0 generates coherent motion between the two frames.
It supports 720p, 1080p, and 4K output, with video duration from 3 to 15 seconds set per request.
Kling 3.0 supports 16:9, 9:16, and 1:1. When reference images are provided, the aspect ratio is adapted automatically from the images.