# Kling O3 4K Video to Video Edit - Core.Today AI API

> Kling O3 native 4K video editing via Fal.AI. Edits an existing video (cited as @Video1) from a text instruction — change the environment, restyle the scene, or swap a subject for an element image (@Element1) — keeping the original motion and timing, and outputs native 4K directly. Input clips of 3-15 seconds.

- **Provider**: Kuaishou
- **Model ID**: fal-ai/kling-video/o3/4k/video-to-video/edit
- **Category**: Video Generation
- **Credits**: 4890 per 5s 4K clip — billed per second of output (= measured input clip length), 977/s
- **Speed**: Slow
- **Quality**: Ultra

## Features
- Text-instructed editing of an existing clip — environment, style, or subject swaps
- Keeps the original motion, timing, and (optionally) audio
- Native 4K output in one step — no upscaling pass
- Element references (@Element1) for subject replacement and style images (@Image1)
- Billed by the measured length of the input clip

## Use Cases
- Season or weather changes on existing footage (summer to snow)
- Swapping a product, animal, or character in a shot
- Restyling live-action footage into an illustrated look
- 4K deliverables for ads without a separate upscale step

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - Edit instruction. Refer to the input video as @Video1, element images as @Element1, and style images as @Image1. Max 2500 characters
- **video_url**: string - Video to edit. .mp4/.mov, 3-15 seconds, 720-3840px, 23-60 fps, max 200MB. The output keeps this clip's length and is billed by its measured duration

### Optional
- **elements**: array - Characters/objects to include, each with a frontal_image_url and 1-3 reference_image_urls; cited as @Element1, @Element2. Elements plus image_urls total at most 4
- **image_urls**: array - Style/appearance reference images, cited as @Image1, @Image2. Elements plus image_urls total at most 4
- **keep_audio**: boolean (default: true) - Keep the original audio from the input video
- **enable_safety_checker**: boolean (default: true) - Enable the safety checker

## Examples

### Snow Scene with Subject Swap
Turn the environment to snow and replace the animal with an element
```json
{
  "model": "fal-ai/kling-video/o3/4k/video-to-video/edit",
  "input": {
    "prompt": "Change environment to be fully snow as @Image1. Replace animal with @Element1",
    "video_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/video_reference.mp4",
    "elements": [
      {
        "frontal_image_url": "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/element1_front.png",
        "reference_image_urls": [
          "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/element1_reference1.png"
        ]
      }
    ],
    "image_urls": [
      "https://storage.googleapis.com/falserverless/example_inputs/kling-o3/pro-v2v-edit/image_url1.jpg"
    ]
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- The output keeps the input clip's length — trim the source to the part you need before editing
- Clips must be 3-15 seconds, at least 720px per side, and 23-60 fps
- Elements plus image_urls may total at most 4 references
- Set keep_audio to false to drop the original soundtrack

## Documentation
https://fal.ai/models/fal-ai/kling-video/o3/4k/video-to-video/edit