Name: Kuaishou Kling 4.0 Video Generator and Editor API
Brand: magicapi
SKU: api-magicapi-text-to-video-generator-api-kwaivgi-kling-v4-0
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎬 Video Generator and Editor API (Kuaishou Kling 4.0)

## Overview
Kling 4.0 is a video model from Kuaishou. Its developer describes it as generating 3 to 30 second videos at up to 1080p from text, keyframes, reference images or reference videos, and editing existing videos.

Send a text `prompt` and a `duration` to generate a video. Add `start_image`, `middle_images` and `end_image` to set keyframes, `reference_images` for characters, objects, scenes or style, and `reference_videos` for motion, camera work or style. Set `base_video` to edit an existing video instead. Each request returns the URL of one video.

## Features
- **Text to video**: 3 to 30 seconds (`duration`, default 5) at `720p` or `1080p` (default).
- **Keyframes**: `start_image`, `middle_images` (in order) and `end_image` set the first, middle and last frames.
- **Reference images and videos**: up to 10 images in total across all image inputs, plus `reference_videos` of 3 to 30 seconds each.
- **Video editing**: `base_video` (3 to 30 seconds) is edited according to the prompt; the output keeps its length and aspect ratio.
- **Prompt references**: refer to inputs in the prompt as `@image_1`, `@image_2`, ... and `@video_1`, `@video_2`, ....
- **Aspect ratios**: `16:9` (default), `9:16`, `1:1`, `21:9`. Ignored when a keyframe image or `base_video` is set.
- **Long prompts**: up to 26,000 English characters or 11,000 non-English characters.

## Use Cases
1. **Short clips from text**: scenes for ads, social posts and concept previews.
2. **Keyframe animation**: move between a start frame, middle frames and an end frame you supply.
3. **Consistent characters and products**: keep a character, object or style from reference images.
4. **Video edits**: change an existing clip by describing the edit in the prompt.

## Visual Examples
### Example Input
Prompt: "A pianist plays a grand piano on the deck of a ship amid towering waves", 3 seconds at `720p` in `16:9`. No images or videos were sent.

```json
{
  "prompt": "A pianist plays a grand piano on the deck of a ship amid towering waves",
  "duration": 3,
  "resolution": "720p",
  "aspect_ratio": "16:9"
}
```

### Example Output
[Watch the example output](https://blog.api.market/wp-content/uploads/2026/11/kling-v4-0-output-114sct6m-api-market.mp4)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | Yes |  |  | Text prompt describing the video. Refer to images as @image_1, @image_2, ... and videos as @video_1, @video_2, ... (see start_image and reference_images for numbering). Up to 26,000 English characters or 11,000 non-English characters. |
| `start_image` | string (URL) | No | none |  | First frame of the video. Supports .jpg/.jpeg/.png, max 30MB, min 300px, aspect ratio between 2:5 and 5:2. |
| `middle_images` | array of URLs | No | `[]` |  | Keyframes between the first and last frame, in order. Same format requirements as start_image. |
| `end_image` | string (URL) | No | none |  | Last frame of the video. Same format requirements as start_image. |
| `reference_images` | array of URLs | No | `[]` |  | Reference images for characters, objects, scenes or style. Images are numbered in this order: start_image, middle_images, end_image, reference_images. Up to 10 images in total across all image inputs. |
| `reference_videos` | array of URLs | No | `[]` |  | Reference videos to take motion, camera work or style from (.mp4/.mov, 3-30 seconds each, 700-4553px per side, max 300MB). Numbered after base_video. |
| `base_video` | string (URL) | No | none |  | Video to edit (.mp4/.mov, 3-30 seconds, 700-4553px per side, max 300MB). Referred to as @video_1. When set, the output keeps the length and aspect ratio of this video. |
| `resolution` | string | No | `1080p` | `720p`, `1080p` | Output resolution. |
| `aspect_ratio` | string | No | `16:9` | `16:9`, `9:16`, `1:1`, `21:9` | Aspect ratio of the output video. Ignored when start_image, middle_images, end_image or base_video is set, since the aspect ratio then comes from the input. |
| `duration` | integer | No | `5` | 3 to 30 | Video duration in seconds. Ignored when base_video is set. |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.115 per API unit.
- **1 API unit = 1 second of output video times the factor of the request's tier, rounded up to a whole unit per request.**
- **Seconds billed**: the requested `duration` when you generate a video. When `base_video` is set, `duration` is ignored and the length of the output video (the length of `base_video`) is billed.
- **Price per second by tier** (unit price x factor):

| Request | `720p` | `1080p` |
| --- | --- | --- |
| Generate (no `base_video`) | $0.19205 per second (x1.67) | $0.2875 per second (x2.5) |
| Edit (`base_video` set) | $0.115 per second (x1) | $0.1725 per second (x1.5) |

- When `resolution` and `base_video` are left out, `1080p` generation applies (x2.5): a default 5-second request is 5 x 2.5 = 12.5, rounded up to 13 units ($1.495).
- Keyframe images, reference images, reference videos, `aspect_ratio` and the prompt do not change the tier.
- **Example cost**: the example generated 3 seconds at `720p` without `base_video`: 3 x 1.67 = 5.01, rounded up to 6 units ($0.69).
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/text-to-video-generator-api-kwaivgi-kling-v4-0`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/text-to-video-generator-api-kwaivgi-kling-v4-0/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "kwaivgi/kling-v4.0",
    "input": {
      "prompt": "A pianist plays a grand piano on the deck of a ship amid towering waves",
      "duration": 3,
      "resolution": "720p",
      "aspect_ratio": "16:9"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "114sct6mf1rmr0d1mvm8qjm01r",
  "version": "kwaivgi/kling-v4.0",
  "status": "starting",
  "created_at": "2026-11-04T14:13:59.032Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/text-to-video-generator-api-kwaivgi-kling-v4-0/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "114sct6mf1rmr0d1mvm8qjm01r",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/11/kling-v4-0-output-114sct6m-api-market.mp4",
  "error": null,
  "created_at": "2026-11-04T14:13:59.032Z",
  "started_at": "2026-11-04T14:13:59.045Z",
  "completed_at": "2026-11-04T14:16:44.414Z"
}
```

`output` is a single URL string pointing to the generated MP4 video.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `prompt`, a `duration` outside 3 to 30, or a `resolution` other than `720p` or `1080p`.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/text-to-video-generator-api-kwaivgi-kling-v4-0";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "kwaivgi/kling-v4.0", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
  "prompt": "A pianist plays a grand piano on the deck of a ship amid towering waves",
  "duration": 3,
  "resolution": "720p",
  "aspect_ratio": "16:9"
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/text-to-video-generator-api-kwaivgi-kling-v4-0"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "kwaivgi/kling-v4.0", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "prompt": "A pianist plays a grand piano on the deck of a ship amid towering waves",
    "duration": 3,
    "resolution": "720p",
    "aspect_ratio": "16:9"
}))
```

## FAQ
- **How do I edit an existing video?**
  - Send it as `base_video` (.mp4 or .mov, 3 to 30 seconds, 700 to 4553 px per side, max 300 MB) and describe the edit in `prompt`, referring to it as `@video_1`. The output keeps its length and aspect ratio, and `duration` is ignored.
- **How do I refer to my images in the prompt?**
  - Images are numbered in this order: `start_image`, `middle_images`, `end_image`, `reference_images`. Use `@image_1`, `@image_2`, ... in the prompt. Videos are `@video_1`, `@video_2`, ..., with `base_video` first.
- **Why was `aspect_ratio` ignored?**
  - When `start_image`, `middle_images`, `end_image` or `base_video` is set, the aspect ratio comes from that input.
- **Why did 3 seconds cost 6 units?**
  - Generating at `720p` bills 1.67 units per second. 3 x 1.67 = 5.01, and each request is rounded up to a whole unit, so it is 6 units ($0.69).
- **How long does a request take?**
  - The example 3-second `720p` video took about 165 seconds to generate. Poll the status endpoint until it finishes.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page.


Create 3 to 30 second videos at 720p or 1080p with Kling 4.0 from text, keyframes and references, or edit a video. From $0.115 per second, pay as you go.

Kuaishou Kling 4.0 Video Generator and Editor API