# Topaz Upscale Video

Topaz Video Upscale uses advanced AI enhancement to intelligently increase video resolution while maintaining natural motion, clarity, and fine detail. It’s ideal for restoring low-quality footage or upgrading older videos to professional-grade quality without compromising realism.

## API Information

- **Model Slug:** topaz-upscale-video
- **Branded URL:** https://www.eachlabs.ai/topaz/topaz/topaz-upscale-video
- **Provider:** Topaz Labs
- **Category:** Video to Video
- **Output Type:** video
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** 8K+ $0.15/s
- **Estimated Processing Time:** 35 seconds
- **Last Updated:** 2026-07-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/topaz-upscale-video

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** 8K+ $0.15/s

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| output.short_side <= "720" | <=720p $0.01/s |
| output.short_side <= "1080" AND output.fps >= "29" | <=1080p >=30fps $0.04/s |
| output.short_side <= "1080" | <=1080p $0.02/s |
| output.short_side <= "2160" AND output.fps >= "59" | <=2160p >=60fps $0.16/s |
| output.short_side <= "2160" | <=2160p $0.08/s |
| output.fps >= "59" | 8K+ >=60fps $0.30/s |
| Rule 7 | 8K+ $0.15/s |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| video_url | string | Yes | - | - | URL of the video to upscale |
| upscale_factor | number | No | 2 | 1–4 | Factor to upscale the video by (e.g. 2.0 doubles width and height) |
| target_fps | integer | No | - | 16–60 | Target FPS for frame interpolation. If set, frame interpolation will be enabled. |
| H264_output | boolean | No | false | - | Whether to use H264 codec for output video. Default is H265. |

## 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": "topaz-upscale-video",
  "input": {
    "video_url": "https://storage.googleapis.com/magicpoint/inputs/topaz-upscale-video-input.mp4"
  }
}'
```

## 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 |

## Overview

**topaz-upscale-video — Video-to-Video AI Model**

Transform low-quality or older footage into professional-grade videos with **topaz-upscale-video**, a video-to-video AI model from the topaz family that uses advanced AI models like Apollo, Chronos, and Aion for intelligent upscaling and frame interpolation. It excels at increasing resolution up to 8K while preserving natural motion, reducing artifacts, and enhancing clarity—ideal for restoring vintage clips or creating smooth slow-motion effects without compromising realism. Developers and creators searching for **topaz video-to-video** solutions or **AI video upscaler** tools find this model delivers cinema-quality results on demanding footage like sports or handheld shots.

## 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.