# Kling 3.0 API

> Cinematic text & image to video with native sound and multi-shot support.

- **Provider**: Kuaishou
- **Model id**: `kling-3-0`
- **Modality**: video
- **Price**: 7.95–38.92 credits /sec

## Overview

Kling 3.0 is called in two steps: create a generation task, then poll the task until the result is ready.

## Authentication

All requests require a Bearer Token in the request header:

```
Authorization: Bearer YOUR_API_KEY
```

## Create Task

`POST https://you.bot/api/v1/generate`

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| modelId | string | Yes | Model id: `kling-3-0` |
| input | object | Yes | Input parameters object (see below) |
| callbackUrl | string | No | https URL we POST the finished task to. Signed with `X-Webhook-Signature` once you create a webhook signing key in Dashboard → Settings |

### input object parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| image_urls | string[] | No | Start Frame / End Frame |
| customize_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. (example: 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) |

### Request example

```json
{
  "modelId": "kling-3-0",
  "input": {
    "image_urls": [
      "https://you.bot/examples/grok-imagine-text-to-image.jpg"
    ],
    "customize_multi_shots": false,
    "sound": true,
    "prompt": "A barista pours latte art in slow motion at a cozy window counter, morning light, steam curling.",
    "duration": 5,
    "aspect_ratio": "1:1",
    "mode": "std"
  }
}
```

### Response example

```json
{
  "taskId": "281e5b0…f39b9",
  "creditsCharged": 58.25
}
```

## Query Task

`GET https://you.bot/api/v1/task/{taskId}?model=kling-3-0`

When `state` is `success`, the output is in `resultUrls`: `{ "state": "success", "resultUrls": [ ... ] }`. (Text models return inline in the create response.)

## Error Codes

| Code | Description |
|------|-------------|
| 200 | Request successful |
| 400 | Invalid request parameters |
| 401 | Authentication failed — check API Key |
| 402 | Insufficient account balance |
| 403 | IP not allowed for this key, or the key is restricted to other models |
| 404 | Task not found, or it has expired |
| 409 | Duplicate request — an identical submit arrived moments ago. Nothing was charged; retry is safe |
| 413 | Payload too large — see the character and file-size limits for this model |
| 429 | Rate limit exceeded — retry after the Retry-After header |
| 500 | Internal server error |
| 504 | Upstream timed out — nothing was delivered; retry is safe |