# Pruna | P-Video 2 Pro

P-Video-2 Pro generates AI video from prompts and optional first or last frames, with 480p/768p quality modes for cinematic clips with audio.

## API Information

- **Model Slug:** p-video-2-pro
- **Branded URL:** https://www.eachlabs.ai/pruna/p-video/p-video-2-pro
- **Provider:** Pruna
- **Category:** Image to Video
- **Output Type:** video
- **Status:** active
- **Base Cost:** $0.01–$0.075 per second, depending on resolution and mode
- **Estimated Processing Time:** 20 seconds
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/p-video-2-pro

## Pricing

- **Charge Type:** dynamic
- **Estimate:** $0.01–$0.075 per second, depending on resolution and mode
- **Pricing Details:** 480p · cost: $0.01
- **Pricing Details:** 480p · speed: $0.02
- **Pricing Details:** 768p · cost: $0.025
- **Pricing Details:** 768p · speed (default): $0.035
- **Pricing Details:** 480p · quality: $0.04
- **Pricing Details:** 768p · quality: $0.075

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| prompt | string | Yes | - | - | Text prompt describing the video scene, motion, style, and audio direction. |
| image | string | No | - | - | Optional image URL to guide the first frame. Supports jpg, jpeg, png, and webp. |
| last_frame_image | string | No | - | - | Optional image URL to guide the final frame. Supports jpg, jpeg, png, and webp. |
| duration | integer | No | 5 | 5–15 | Requested video duration in whole seconds, from 5 to 15. |
| resolution | string | No | 768p | 480p, 768p | Video resolution. 480p is lower cost; 768p is higher detail. |
| aspect_ratio | string | No | 16:9 | 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 1:1 | Output aspect ratio for text-to-video. Reference images determine the canvas when provided. |
| mode | string | No | speed | speed, quality, cost | Generation recipe. Use speed for faster generation, quality for higher-quality output, or cost for lower-cost generation. |
| prompt_upsampler | string | No | turbo | off, turbo, max | Prompt expansion mode before generation. |
| seed | integer | No | - | 1–2147483647 | Optional random seed for reproducible generation. |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "p-video-2-pro",
  "input": {
    "prompt": "Photoreal fashion product film, 8 seconds. Hero: an unstructured red wool overcoat with black buttons, no labels, hanging on a simple wooden hanger in a white studio. Slow push-in, then a slight orbit so the lapel, buttons and wool texture stay readable. Soft daylight. No people, no captions. Audio: quiet studio, a faint fabric rustle from air, no music, no voiceover."
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated video)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.