# Kling 3.0 Turbo API

> Kling 3.0 Turbo — high-quality AI video generation.

- **Provider**: Kling
- **Model id**: `kling-v3-turbo-image-to-video`
- **Modality**: video
- **Price**: 10.42–13.02 credits /sec

## Overview

Kling 3.0 Turbo 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-v3-turbo-image-to-video` |
| 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 |
|-----------|------|----------|-------------|
| prompt | string | Yes | Text description for the video generation Max 2500 characters. (example: Create a stylish **fashion advertisement video** from the uploaded photo, with **multiple scene changes and dynamic fashion-commercial editing** while keeping… — full value in the request example) |
| image_urls | string[] | Yes | URL of the image to be used for the video (image URL) |
| duration | number | Yes | The duration of the generated video in seconds (range 3-15) (default: 5) |
| resolution | string | Yes | Resolution of the generated video (options: 720p \| 1080p) (default: 720p) |

### Request example

```json
{
  "modelId": "kling-v3-turbo-image-to-video",
  "input": {
    "prompt": "Create a stylish **fashion advertisement video** from the uploaded photo, with **multiple scene changes and dynamic fashion-commercial editing** while keeping the same woman visually consistent throughout.\n\nThe subject is a young woman with **short black hair**, wearing a **fitted white t-shirt, light blue denim shorts, white socks, and white sneakers**. Preserve her **exact face, hairstyle, body shape, outfit, and overall identity** across the entire video.\n\nStart with a **clean full-body shot** against the plain light-gray wall. Then **switch between different fashion-ad style shots**: full-body pose, medium shot, close-up portrait, slight angle change, and detail shots of her upper body and legs. Make the cuts feel **smooth, trendy, and premium**, like a modern minimalist fashion campaign.\n\nAdd subtle, realistic motion in each shot:\ngentle blinking, soft breathing, slight head turns, confident eye contact, a faint smile, natural posture shifts, small hand movements, and slight hair movement from a soft breeze.\nInclude **slow camera push-ins, subtle side movement, and elegant reframing** to create visual variety.\n\nUse **scene switching** with a polished editorial feel:\nclean jump cuts, soft match cuts, and stylish transitions between close-up, mid-shot, and full-body framing.\nThe video should feel like a **high-end fashion brand commercial** — minimal, clean, modern, confident, and visually refined.\n\nLighting should remain **soft, bright, natural, and polished**, with a subtle studio-commercial look.\nBackground should stay **minimal and uncluttered**, with only slight framing or angle variation for different shots.\nKeep everything elegant, realistic, and premium.\n\n**Important constraints:**\nDo not change her outfit.\nDo not change her face or hairstyle.\nDo not add extra people or props.\nDo not create heavy or exaggerated motion.\nNo body distortion, no warped hands, no flickering, no messy background changes, and no sudden camera shake.\nMaintain realistic anatomy and a smooth, high-end fashion ad aesthetic throughout.\n\n**Optional shorter version:**\n\nAnimate the uploaded photo into a modern **fashion ad video** with **scene switching** between full-body, medium, and close-up shots. Keep the same woman’s face, short black hair, white t-shirt, denim shorts, white socks, and white sneakers fully consistent. Add subtle blinking, soft breathing, slight head turns, relaxed posture shifts, and gentle hair movement. Use slow camera push-ins,",
    "image_urls": [
      "https://you.bot/examples/grok-imagine-text-to-image.jpg"
    ],
    "duration": 5,
    "resolution": "720p"
  }
}
```

### Response example

```json
{
  "taskId": "281e5b0…f39b9",
  "creditsCharged": 52.08
}
```

## Query Task

`GET https://you.bot/api/v1/task/{taskId}?model=kling-v3-turbo-image-to-video`

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 |