# Grok Imagine Video 1.5 - Core.Today AI API

> xAI's Grok Imagine Video 1.5 preview: image-to-video generation with synchronized audio. An upgraded successor to Grok Imagine Video with flat per-second pricing regardless of resolution.

- **Provider**: xAI
- **Model ID**: xai/grok-imagine-video-1.5
- **Category**: Video Generation
- **Credits**: 930 per 5s video (default) — billed at 187 credits per second, duration 1-15s, same price at 480p and 720p, audio included
- **Speed**: Medium
- **Quality**: High

## Features
- Image-to-video animation with synchronized audio included
- Upgraded 1.5 preview of xAI's Grok Imagine Video
- Flexible 1-15 second duration, billed per second
- 480p and 720p at the same price
- Auto aspect ratio matching the input image, plus 7 explicit ratios

## Use Cases
- Bringing photos and illustrations to life with matching sound
- Short social clips (1-3s) at minimal cost thanks to per-second billing
- Product imagery animated into shareable video ads
- Portrait and landscape social formats from the same source image
- Quick audio-visual previsualization of a still key frame

## 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 describing the motion or scene for the generated video
- **image**: string - Input image to animate (image-to-video). Supports jpg, jpeg, png, webp. Output aspect ratio defaults to the image's native ratio

### Optional
- **duration**: integer (default: 5) - Duration of the video in seconds (1-15)
- **resolution**: string (default: 720p) - Resolution of the video (480p and 720p cost the same)
  Options: 720p, 480p
- **aspect_ratio**: string (default: auto) - Aspect ratio of the output video. 'auto' follows the input image's native ratio
  Options: auto, 16:9, 4:3, 1:1, 9:16, 3:4, 3:2, 2:3

## Examples

### Cinematic Portrait Animation
Animating a still portrait with subtle motion and synced ambience
```json
{
  "model": "xai/grok-imagine-video-1.5",
  "input": {
    "image": "https://replicate.delivery/pbxt/PCRhFZ9wvsy2oylrpkZqa9VyAhDfe7VQi0jOKERQF6tX2ddF/download-4.png",
    "prompt": "Cinematic motion - the woman looks up out into the sunlight filtering into the room.",
    "duration": 5,
    "resolution": "720p",
    "aspect_ratio": "auto"
  }
}
```

### Short Product Teaser (Cost-Optimized)
A 3-second clip costs just 360 credits thanks to per-second billing
```json
{
  "model": "xai/grok-imagine-video-1.5",
  "input": {
    "image": "https://example.com/product-shot.png",
    "prompt": "Slow camera push-in on the sneaker as studio lights sweep across it, subtle dust particles in the air",
    "duration": 3,
    "resolution": "720p",
    "aspect_ratio": "1:1"
  }
}
```

## 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
- 480p and 720p cost exactly the same (120/s), so there is no reason to drop below 720p for quality
- Duration is fully flexible from 1 to 15 seconds and billed per second — trim to the shortest length that works to save credits
- Synchronized audio is always included at no extra charge, unlike models that bill extra for audio
- Both prompt and image are required — this is a pure image-to-video model, not text-to-video
- Leave aspect_ratio on 'auto' to preserve the input image's framing, or pick one of 7 explicit ratios to reformat

## Documentation
https://replicate.com/xai/grok-imagine-video-1.5