Topaz Video Upscaler API: parameters, code samples, Studio

Name: Topaz Video Upscaler API
Brand: Topaz Labs
Price: 0.1100 USD
Availability: InStock

Examples

What Topaz Video Upscaler can do

Topaz Video - Upscale: after (before clip in before_url)

Topaz Video - Nyx XL denoise model: after (before clip in before_url)

Official examples from the model vendor: Topaz Labs.

Topaz Video Upscaler brings Topaz Labs' video upscaling and restoration to the Jantaris API. It takes a source video and upscales it 2x; on Jantaris the factor is fixed, and the 1x cleanup and 4x options are not exposed yet. It accepts MP4, MOV or MKV files up to 50 MB and preserves the clip's duration and frame timing, so the result drops straight back into an edit. Billing is per second of the source length as measured on the server.

Best for

Upscaling AI video clips to 4K for delivery
Restoring compressed social or phone footage
Bringing 1080p sources up to 4K
Finishing short clips from models like Seedance 2.0 Fast

Prompting tips

A 1080p source comes back at about 4K, a 720p source at about 1440p.
Trim the clip before uploading, since you pay per second of source.
Keep files under 50 MB and split longer videos into parts.
For a specific target resolution, use Enhance Video 1.0 instead.

FAQ

How much does the Topaz Video Upscaler API cost?

The rate is $0.11 per second, charged per second of the source video. Failed jobs are not charged.

What file formats and sizes are accepted?

MP4, MOV or MKV, up to 50 MB, passed as a public URL.

Does upscaling change the frame rate or length?

No. Duration and frame timing are preserved. If you want to pick the output resolution, see Enhance Video 1.0.

How to call Topaz Video Upscaler via API

curl https://jantaris.com/v1/generate?wait=60 \
  -H "Authorization: Bearer $JANTARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "topaz-video-upscaler",
  "input": {
    "video_url": "https://example.com/input.mp4"
  }
}'

import os, time, requests

API = "https://jantaris.com/v1"
H = {"Authorization": f"Bearer {os.environ['JANTARIS_API_KEY']}"}

task = requests.post(f"{API}/generate", headers=H, json={
    "model": "topaz-video-upscaler",
    "input": {
        "video_url": "https://example.com/input.mp4"
    }
}).json()
while task["status"] in ("queued", "running"):
    time.sleep(3)
    task = requests.get(f"{API}/tasks/{task['id']}", headers=H).json()

print(task["status"], task["cost"], [o["url"] for o in task["output"]])

const API = "https://jantaris.com/v1";
const headers = { Authorization: `Bearer ${process.env.JANTARIS_API_KEY}`, "Content-Type": "application/json" };

let task = await (await fetch(`${API}/generate`, {
  method: "POST",
  headers,
  body: JSON.stringify({
    "model": "topaz-video-upscaler",
    "input": {
      "video_url": "https://example.com/input.mp4"
    }
  }),
})).json();

while (task.status === "queued" || task.status === "running") {
  await new Promise((r) => setTimeout(r, 3000));
  task = await (await fetch(`${API}/tasks/${task.id}`, { headers })).json();
}
console.log(task.status, task.cost, task.output.map((o) => o.url));