Kling 4.0 API

Complete API reference for Kling 4.0 video generation models by Kuaishou.

Model Variants

This API supports five model variants:

Quick Comparison

Supported Aspect Ratios

Text-to-Video, Image-to-Video, Reference-to-Video, and Video Edit support:

16:9, 9:16, 1:1, 21:9

The default is 16:9. Video Extend does not support the aspect_ratio parameter; the output follows the source video's aspect ratio.

Resolution Options

All five models require resolution and duration. Include resolution explicitly even though its default value is 720p. duration has no default value.

Kling 4.0 Text to Video

Endpoint

POST /api/v1/video/task

Request Parameters

Required

Optional

Example Request

javascriptCopy
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-v4.0-text-to-video',
    prompt: 'A drone flying over a mountain range at sunrise, smooth forward camera movement',
    resolution: '720p',
    duration: 5,
    aspect_ratio: '16:9'
  })
});

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

Kling 4.0 Image to Video

Request Parameters

Required

Optional

When both image_url and image_end_url are provided, key_frames can contain at most 8 images. Intermediate frames are used in array order; their timing is determined by the model.

Example Request

javascriptCopy
{
  model_name: 'kling-v4.0-image-to-video',
  prompt: 'Camera slowly pulls back from the character to reveal the surrounding mountain landscape',
  image_url: 'https://example.com/start-frame.jpg',
  image_end_url: 'https://example.com/end-frame.jpg',
  key_frames: [
    'https://example.com/middle-frame-1.jpg',
    'https://example.com/middle-frame-2.jpg'
  ],
  resolution: '720p',
  duration: 8,
  aspect_ratio: '16:9'
}

Kling 4.0 Reference to Video

Request Parameters

Required

Optional

Reference images, videos, and audio are all optional. Provide any one media type, combine media types, or omit all three.

The output duration is independently set to 3-30 seconds and does not count toward the reference videos' combined duration limit.

Example Request

javascriptCopy
{
  model_name: 'kling-v4.0-reference-to-video',
  prompt: 'Use the character from the reference image, follow the camera movement in the reference video, and use the reference audio for voice guidance',
  images: ['https://example.com/character-reference.jpg'],
  videos: ['https://example.com/motion-reference.mp4'],
  audios: ['https://example.com/voice-reference.mp3'],
  keep_original_sound: false,
  resolution: '720p',
  duration: 8,
  aspect_ratio: '16:9'
}

Kling 4.0 Video Edit

Request Parameters

Required

Optional

Example Request

javascriptCopy
{
  model_name: 'kling-v4.0-video-edit',
  prompt: 'Replace the background with warm sunset colors while preserving the subject and camera movement',
  video_url: 'https://example.com/source.mp4',
  images: ['https://example.com/sunset-reference.jpg'],
  keep_original_sound: true,
  resolution: '720p',
  duration: 8,
  aspect_ratio: '16:9'
}

Kling 4.0 Video Extend

Request Parameters

Required

Optional

Do not send aspect_ratio; the output follows the source video's aspect ratio. The result contains the full video, including the source and the extension. Its total duration is the source video duration plus duration.

Example Request

javascriptCopy
{
  model_name: 'kling-v4.0-video-extend',
  prompt: 'Continue the camera movement forward through the valley as the sun rises above the mountains',
  video_url: 'https://example.com/source.mp4',
  image_end_url: 'https://example.com/target-end-frame.jpg',
  resolution: '720p',
  duration: 5
}

Billing Rules

Text-to-Video and Image-to-Video are billed by output resolution and generated video duration. Video Extend is billed by resolution and the added segment's duration, not the full returned video length.

Reference-to-Video requests containing reference videos and Video Edit requests account for both input and output video duration at the selected resolution. Input video duration has a minimum billed duration of 3 seconds and a maximum of 30 seconds. For multiple reference videos, these bounds apply to their combined duration, not to each video separately. Billing duration bounds do not define upload limits.

Without reference videos, Reference-to-Video uses the same billing rules as Text-to-Video, whether or not reference images or audio are supplied. For requests with video input, supported reference images, reference audio, and keep_original_sound do not add separate charges.

Response Format

Initial Response

All models return a task_id for polling:

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

Poll with GET /api/v1/video/{task_id} to check status and retrieve the generated video.

Status Values

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

Best Practices

1. Required Parameters: Always provide resolution and duration, including when using the default 720p resolution
2. Frame Count: Keep the combined first, ending, and intermediate frames at 10 or fewer
3. Reference Media: Keep reference media within the documented counts and durations
4. Original Sound: Use keep_original_sound only for Reference-to-Video or Video Edit
5. Video Extension: Set duration to the additional length and omit aspect_ratio