# Pruna P-Video - Core.Today AI API

> PrunaAI's fast video generator with a built-in draft mode for rapid creative iteration. Text-to-video, image-to-video, and audio-conditioned generation in a single endpoint, with clips up to 20 seconds — one of the longest durations on the platform.

- **Provider**: Pruna AI
- **Model ID**: prunaai/p-video
- **Category**: Video Generation
- **Credits**: 240 per second — 720p standard 47/s, 720p draft 13/s, 1080p standard 94/s, 1080p draft 24/s; duration 1-20s (default 5s at 720p standard = 240)
- **Speed**: Fast
- **Quality**: Standard

## Features
- Built-in draft mode: lower-quality previews at roughly a quarter of the standard price
- Text-to-video and image-to-video in one endpoint (image parameter)
- Optional audio input (flac/mp3/wav) to condition video generation
- Up to 20 second duration — one of the longest on the platform
- 720p or 1080p output with last-frame conditioning and 7 aspect ratios

## Use Cases
- Rapid creative iteration: cheap draft renders before the final standard-quality pass
- Long-form clips (10-20s) that most video models cannot produce in one shot
- Animating product or portrait photos via image-to-video
- Music- or narration-driven clips using the audio conditioning input
- High-resolution 1080p hero shots for landing pages and ads

## 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
- **last_frame_image**: string - Reference image for the last frame of the video. Supports jpg, jpeg, png, webp
- **audio**: string - Input audio to condition video generation. Supports flac, mp3, wav
- **duration**: integer (default: 5) - Duration of the video in seconds (1-20). Ignored when audio is provided
- **aspect_ratio**: string (default: 16:9) - Aspect ratio of the video. Ignored when an input image is provided
  Options: 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 1:1
- **resolution**: string (default: 720p) - Resolution of the video (1080p doubles the per-second price)
  Options: 720p, 1080p
- **fps**: integer (default: 24) - Frames per second of the video
  Options: 24, 48
- **draft**: boolean (default: false) - Draft mode: generates a lower-quality preview at roughly a quarter of the price
- **prompt_upsampling**: boolean (default: true) - Use prompt upsampling to enhance the prompt
- **disable_safety_filter**: boolean (default: true) - Disable safety filter for prompts (and input image). When disabled, prompts are not checked for unsafe content before generation.
- **save_audio**: boolean (default: true) - Save the video with audio
- **seed**: integer - Random seed. Set for reproducible generation
- **no_op**: boolean (default: false) - Health check mode - returns status without inference.

## Examples

### Image-to-Video (720p Standard)
Animate a still image with a prompt at standard quality — 5s at 30/s = 150 credits
```json
{
  "model": "prunaai/p-video",
  "input": {
    "fps": 24,
    "draft": false,
    "image": "https://replicate.delivery/pbxt/OejQrIXERvqS9kpygH9PfQZDOIdzkD6GKytAXxedNSyyRtej/9.png",
    "prompt": "The prune says \"And this, kids, is how you generate a video in less than 10 seconds\".",
    "duration": 5,
    "resolution": "720p",
    "save_audio": true,
    "aspect_ratio": "16:9",
    "prompt_upsampling": false
  }
}
```

### Draft Mode Preview (Cost-Optimized)
A quick 10s text-to-video preview in draft mode — 10s at 8/s = 80 credits
```json
{
  "model": "prunaai/p-video",
  "input": {
    "prompt": "A paper boat drifting down a rain-soaked city street at night, neon reflections",
    "draft": true,
    "duration": 10,
    "resolution": "720p",
    "aspect_ratio": "9:16"
  }
}
```

## 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
- Use draft mode for iteration: 720p draft is 8/s vs 30/s standard — explore prompts cheaply, then re-render the winner with draft: false
- Billing is per second, so a 20s clip at 720p standard costs 600 credits — trim duration to what you actually need
- 1080p doubles the per-second price (60/s standard, 15/s draft) — reserve it for final hero renders
- When an audio file is provided, duration is ignored and follows the audio — check audio length before submitting
- aspect_ratio is ignored in image-to-video mode; the output follows the input image's framing

## Documentation
https://replicate.com/prunaai/p-video