Name: Pruna AI P-Video-Upscale Video Upscaler API
Brand: magicapi
SKU: api-magicapi-video-upscaler-high-resolution-prunaai-p-video-upscale
Availability: InStock
Author: API Market

Shashank Agarwal

# 📈 Video Upscaler API (Pruna AI P-Video-Upscale)

## Overview
P-Video-Upscale is a video upscaler from Pruna AI. Its developer describes it as turning a low-resolution clip into a sharper 720p, 1080p, 2K or 4K MP4 that keeps the original aspect ratio and audio, with optional frame interpolation up to 60 fps.

Send a `video` URL and pick the output resolution with `target`. Set `fps` to change the output frame rate (a rate higher than the input is interpolated) or leave it empty to keep the input's frame rate. Each request returns the URL of one MP4 video.

## Features
- **Four resolution targets**: `720p`, `1080p` (default), `2k`, `4k`.
- **Frame rate control**: `fps` from 16 to 60. Leave it empty to keep the input video's frame rate (up to 60 fps); a higher rate than the input is interpolated.
- **Keeps aspect ratio and audio**: according to its developer, the output keeps the input's aspect ratio and audio track.
- **Turbo mode**: `turbo` (default `false`) gives faster generation for slightly lower quality.

## Use Cases
1. **Old or low-resolution footage**: bring small clips up to 720p or 1080p for modern screens.
2. **Smoother motion**: raise a 24 fps clip to a higher frame rate with interpolation.
3. **Generated video**: upscale short clips from video generation models that output at low resolution.
4. **Delivery formats**: produce 2K or 4K versions of a clip for platforms that require them.

## Visual Examples
### Example Input
Video: [Watch the example input (2 s, 240p)](https://blog.api.market/wp-content/uploads/2026/11/video-upscale-penguin-240p-w15-input-api-market.mp4)

Settings: `target` `720p`, `fps` `24`, `turbo` `false`.

### Example Output
[Watch the example output (720p, 24 fps, 1.96 s)](https://blog.api.market/wp-content/uploads/2026/11/p-video-upscale-output-jj3fkwnx-api-market.mp4)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `video` | string (URL) | Yes |  |  | Input video to upscale |
| `target` | string | No | `1080p` | `720p`, `1080p`, `2k`, `4k` | Output resolution target |
| `fps` | integer | No | none | 16 to 60 | Output frame rate. Leave empty to keep the input video's frame rate (up to 60 fps); a higher rate than the input is interpolated |
| `turbo` | boolean | No | `false` |  | Faster generation for slightly lower quality |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.012 per API unit.
- **Billing**: the length of the output video in seconds, rounded up per request, times a factor set by `target` and `fps`.

| `target` | Factor at 16 to 30 fps | Price per second at 16 to 30 fps | Factor at 31 to 60 fps | Price per second at 31 to 60 fps |
| --- | --- | --- | --- | --- |
| `720p` | 1 | $0.012 | 2 | $0.024 |
| `1080p` | 2 | $0.024 | 4 | $0.048 |
| `2k` | 4 | $0.048 | 8 | $0.096 |
| `4k` | 8 | $0.096 | 16 | $0.192 |

- When `target` is omitted, the `1080p` row applies. When `fps` is omitted, the request is billed at the 31 to 60 fps rate, even if the output keeps a lower input frame rate. Send `fps` explicitly (for example `24` or `30`) to be billed at the 16 to 30 fps rate.
- Example: the request above produced 1.96 seconds of 720p video at 24 fps, rounded up to 2 seconds x factor 1 = 2 API units = $0.024.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/video-upscaler-high-resolution-prunaai-p-video-upscale`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 2 seconds and an overall timeout of 900 seconds (15 minutes) work well. Longer clips and higher targets take longer.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/video-upscaler-high-resolution-prunaai-p-video-upscale/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "prunaai/p-video-upscale",
    "input": {
      "video": "https://blog.api.market/wp-content/uploads/2026/11/video-upscale-penguin-240p-w15-input-api-market.mp4",
      "target": "720p",
      "fps": 24,
      "turbo": false
    }
  }'
```

Response (201 Created):
```json
{
  "id": "jj3fkwnxh1rmy0d1mvnsfs2x5w",
  "version": "prunaai/p-video-upscale",
  "status": "starting",
  "created_at": "2026-11-04T14:17:09.768Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/video-upscaler-high-resolution-prunaai-p-video-upscale/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "jj3fkwnxh1rmy0d1mvnsfs2x5w",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/11/p-video-upscale-output-jj3fkwnx-api-market.mp4",
  "error": null,
  "created_at": "2026-11-04T14:17:09.768Z",
  "started_at": "2026-11-04T14:17:09.782Z",
  "completed_at": "2026-11-04T14:17:20.924Z"
}
```

`output` is a single URL string pointing to the upscaled MP4 video.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `video`, a `target` that is not in the list, or an `fps` outside 16 to 60.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`, for example when the video URL cannot be downloaded; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/video-upscaler-high-resolution-prunaai-p-video-upscale";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "prunaai/p-video-upscale", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 900000;
  const pollInterval = 2000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 15 minutes");
}

createAndWaitForPrediction({
  video: "https://blog.api.market/wp-content/uploads/2026/11/video-upscale-penguin-240p-w15-input-api-market.mp4",
  target: "720p",
  fps: 24,
  turbo: false
}).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/video-upscaler-high-resolution-prunaai-p-video-upscale"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "prunaai/p-video-upscale", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 900
    poll_interval = 2
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 15 minutes")


print(create_and_wait_for_prediction({
    "video": "https://blog.api.market/wp-content/uploads/2026/11/video-upscale-penguin-240p-w15-input-api-market.mp4",
    "target": "720p",
    "fps": 24,
    "turbo": False
}))
```

## FAQ
- **How is a request priced?**
  - Output seconds, rounded up, times the factor for your `target` and `fps` (see the Pricing table). A 5 second clip at 1080p and 30 fps is 5 x 2 = 10 units ($0.12).
- **What happens if I leave `fps` empty?**
  - The output keeps the input's frame rate (up to 60 fps), but the request is billed at the 31 to 60 fps rate. Send the frame rate you want, such as `24` or `30`, to pay the lower rate.
- **Can it increase the frame rate?**
  - Yes. Set `fps` higher than the input's frame rate (up to 60) and the extra frames are interpolated.
- **Does the output keep my audio?**
  - Its developer states that the output keeps the original aspect ratio and audio.
- **What does `turbo` do?**
  - It gives faster generation for slightly lower quality. The price is the same with or without it.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page.


Upscale low-resolution video to 720p, 1080p, 2K or 4K MP4 with Pruna AI's P-Video-Upscale, with optional frame interpolation up to 60 fps. From $0.012 per output second, pay as you go.