# Grok Imagine Video - Core.Today AI API

> Generate videos using xAI's Grok Imagine Video model. Supports text-to-video, image-to-video, and editing an existing short video clip.

- **Provider**: xAI
- **Model ID**: xai/grok-imagine-video
- **Category**: Video Generation
- **Credits**: 580 per 5s video (default) — billed per second (117/s, 1-15s)
- **Speed**: Fast
- **Quality**: High

## Features
- Flat per-second pricing regardless of resolution or aspect ratio
- Text-to-video and image-to-video generation
- Video editing mode — modify an existing short clip (up to 8.7s) with a prompt
- 480p or 720p output, up to 15 seconds
- Auto aspect ratio detection from the input image

## Use Cases
- Quick text-to-video clips for social content
- Animating a still image into short motion
- Editing an existing video clip with a text instruction
- Iterating on video length up to 15 seconds at a flat rate
- Vertical or square clips using explicit aspect ratios

## 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 - Text prompt for video generation

### Optional
- **image**: string - Input image to generate video from (image-to-video). Supports jpg, jpeg, png, webp
- **video**: string - Input video to edit (video editing mode). Direct link, max 8.7 seconds. mp4, mov, webm
- **duration**: integer (default: 5) - Duration of the video in seconds (1-15). Ignored when editing a video
- **resolution**: string (default: 720p) - Resolution of the video. Ignored when editing a video
  Options: 720p, 480p
- **aspect_ratio**: string (default: auto) - Aspect ratio. Defaults to 16:9 for text-to-video, or the input image's ratio for image-to-video. Ignored when editing a video
  Options: auto, 16:9, 4:3, 1:1, 9:16, 3:4, 3:2, 2:3

## Examples

### Text-to-Video (720p)
Generate a 5-second clip directly from a text prompt
```json
{
  "model": "xai/grok-imagine-video",
  "input": {
    "prompt": "a penguin walks away from the camera, towards a large snowy mountaintop in the distance",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "16:9"
  }
}
```

### Longer Clip (15s)
The maximum 15-second duration, still billed at the same flat per-second rate
```json
{
  "model": "xai/grok-imagine-video",
  "input": {
    "prompt": "a lone astronaut walking across a red Martian desert as twin suns set on the horizon",
    "duration": 15,
    "resolution": "480p",
    "aspect_ratio": "21:9"
  }
}
```

## 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
- Pricing is a flat $0.05/sec regardless of resolution or aspect ratio — pick 720p unless file size matters
- Duration ranges 1-15 seconds; longer clips cost proportionally more with no per-second discount
- In video editing mode, duration and resolution inputs are ignored (the source clip's length is kept)
- aspect_ratio: auto lets the model infer 16:9 for text prompts or match your input image automatically

## Documentation
https://replicate.com/xai/grok-imagine-video