# Grok Imagine Video Edit

> Edit an existing video with xAI's Grok Imagine Video model. Output inherits the source video's duration and resolution (720p cap).

- **Provider**: xai-video-edit
- **Model ID**: xai/grok-imagine-video/edit
- **Category**: video_editing
- **Credits**: 2790 per request
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `duration` (integer, optional): Billing hint - the length of your source video in seconds. xAI ignores this parameter; output always matches the source length. Omitting it bills the 15-second maximum. (Default: `15`; Range: min: 1, max: 15)
- `prompt` (string, **required**): Text prompt describing the edit.
- `video` (string, **required**): Source video URL to edit. Output inherits its duration, resolution (720p cap) and aspect ratio.

## Example Request

```json
{
  "model": "xai/grok-imagine-video/edit",
  "input": {
    "duration": 5,
    "prompt": "Add gentle falling snow to the scene",
    "video": "https://files.core.today/aiapi/e71478061c13d5dc/public/ppORKQhfT3NdgogCcLKVKvHN0MaWbduq/0.mp4"
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

xai, grok, video-editing

## Documentation

https://docs.x.ai/developers/model-capabilities/video/editing