# Kling 3.0 API

Complete API reference for Kling 3.0 video generation models by Kuaishou.

## Model Variants

This API supports four model variants:

| Model | ID | Tier | Description |
|-------|-----|------|-------------|
| **Kling 3.0 Std Text to Video** | `kling-v3.0-std-text-to-video` | Standard | Text-to-video generation at standard quality |
| **Kling 3.0 Std Image to Video** | `kling-v3.0-std-image-to-video` | Standard | Image-to-video animation at standard quality |
| **Kling 3.0 Pro Text to Video** | `kling-v3.0-pro-text-to-video` | Pro | Text-to-video generation at pro quality |
| **Kling 3.0 Pro Image to Video** | `kling-v3.0-pro-image-to-video` | Pro | Image-to-video animation at pro quality |

## Quick Comparison

| Feature | Std | Pro |
|---------|-----|-----|
| Quality | Standard | Highest |
| Generation Speed | Faster | Slower |
| Aspect Ratios | 16:9, 9:16, 1:1 | 16:9, 9:16, 1:1 |
| Duration Range | 3-15 seconds | 3-15 seconds |

| Feature | Text to Video | Image to Video |
|---------|---------------|----------------|
| Input | Text prompt | Image + Text prompt |
| Start Frame | Not supported | Required |
| End Frame | Not supported | Not supported |
| Audio | Optional | Optional |

### Supported Aspect Ratios

| Ratio | Description |
|-------|-------------|
| `16:9` | Landscape (widescreen) |
| `9:16` | Portrait (vertical) |
| `1:1` | Square |

## Kling 3.0 Text to Video (Std & Pro)

### Endpoint

```
POST /api/v1/video/task
```

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model_name` | string | `"kling-v3.0-std-text-to-video"` or `"kling-v3.0-pro-text-to-video"` |
| `prompt` | string | Video generation prompt |
| `duration` | number | Video duration in seconds (3-15) |
| `aspect_ratio` | string | Video aspect ratio: `"16:9"`, `"9:16"`, or `"1:1"` |

#### Optional

| Parameter | Type | Description |
|-----------|------|-------------|
| `sound` | boolean | Generate ambient sound for the video |
| `guidance_scale` | number | Prompt adherence strength, float between 0 and 1 |
| `negative_prompt` | string | Elements to exclude from the generated video |

### Example Request

**Std Version:**

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'kling-v3.0-std-text-to-video',
    prompt: 'A fox running through a snowy forest at dusk',
    duration: 5,
    aspect_ratio: '16:9'
  })
});

const { data } = await response.json();
const taskId = data.task_id;
```

**Pro Version:**

```javascript
{
  model_name: 'kling-v3.0-pro-text-to-video',
  prompt: 'A fox running through a snowy forest at dusk',
  duration: 5,
  aspect_ratio: '16:9'
}
```

## Kling 3.0 Image to Video (Std & Pro)

### Request Parameters

#### Required

| Parameter | Type | Description |
|-----------|------|-------------|
| `model_name` | string | `"kling-v3.0-std-image-to-video"` or `"kling-v3.0-pro-image-to-video"` |
| `prompt` | string | Video generation prompt |
| `duration` | number | Video duration in seconds (3-15) |
| `aspect_ratio` | string | Video aspect ratio: `"16:9"`, `"9:16"`, or `"1:1"` |
| `image_url` | string | The first frame of the video |

#### Optional

| Parameter | Type | Description |
|-----------|------|-------------|
| `sound` | boolean | Generate ambient sound for the video |
| `guidance_scale` | number | Prompt adherence strength, float between 0 and 1 |
| `negative_prompt` | string | Elements to exclude from the generated video |

### Example Request

**Std Version:**

```javascript
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'kling-v3.0-std-image-to-video',
    image_url: 'https://example.com/image.jpg',
    prompt: 'Gentle breeze, leaves rustling, slow camera pull back',
    duration: 5,
    aspect_ratio: '16:9'
  })
});

const { data } = await response.json();
const taskId = data.task_id;
```

**Pro Version:**

```javascript
{
  model_name: 'kling-v3.0-pro-image-to-video',
  image_url: 'https://example.com/image.jpg',
  prompt: 'Gentle breeze, leaves rustling, slow camera pull back',
  duration: 5,
  aspect_ratio: '16:9'
}
```

## Response Format

### Initial Response

```json
{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "{task_id}",
    "response_url": "https://api.flaq.ai/api/v1/video/{task_id}",
    "task_status": "submitted"
  }
}
```

### Polling Response

Poll `GET /api/v1/video/{taskId}` to check status:

```json
{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "{task_id}",
    "response_url": "https://api.flaq.ai/api/v1/video/{task_id}",
    "task_status": "succeed",
    "task_status_msg": null,
    "task_result": {
      "credit": 0.2,
      "videos": [
        {
          "url": "https://example.com/generated-video.mp4"
        }
      ]
    }
  }
}
```

### Status Values

- `submitted`: Task accepted and waiting to be processed
- `processing`: Video generation in progress
- `succeed`: Video generation completed
- `failed`: Video generation failed

## Processing Time

- **Std Version**: ~2-4 minutes depending on duration
- **Pro Version**: ~3-6 minutes depending on duration

Poll every 5-10 seconds. Longer videos (10-15 seconds) may take additional time.

## Best Practices

1. **Describe Motion Clearly**: Include camera movements and subject actions in the prompt for more dynamic results
2. **Use Negative Prompts**: Exclude unwanted elements (e.g., `"blurry, low quality, watermark"`) to improve output
3. **Guidance Scale**: Lower values (0.3-0.5) allow more creative freedom; higher values (0.7-1.0) follow the prompt more strictly
4. **Image Quality**: For image-to-video, use sharp, well-lit input images for best motion quality
5. **Duration**: Start with shorter durations (3-5 seconds) to iterate quickly, then increase for final output
6. **Tier Selection**: Use Std for faster iteration and Pro for final production-quality videos