Enhance Video 1.0 API

Enhance Video 1.0 improves existing footage in one pass: upscaling, denoising, deblocking and color refinement, with output from 240p up to 8K (4K on the lite tier). There are three tiers: lite (fastest, about 27% of the standard cost), standard (the default) and professional (about 10x standard, keeps film grain). The engine also offers frame interpolation, scene presets and 10-16-bit output, but Jantaris does not expose those options yet. Inputs can be up to 10 GB and 2 hours long, with a short side of at most 1440 px.

Best for

• Remastering old film and archive footage
• Improving UGC and phone video for ads
• Upscaling AI-generated clips before a big-screen delivery
• Long-form content of up to 2 hours per file

Prompting tips

• Preview on lite, then render the keeper on standard.
• Choose professional only for grain preservation, since it costs about 10x standard.
• Lite does not support 8K; use standard or professional for 8K output.
• Sources need a short side of 1440 px or less, so downscale larger originals first.

FAQ

How much does Enhance Video 1.0 cost?

Pricing is from $0.0053 per second. Relative to standard, lite costs about 27% and professional about 10x, and failed jobs are not charged.

What is the maximum output resolution?

8K on the standard and professional tiers, 4K on lite.

How long can the input video be?

Up to 2 hours and 10 GB, with a short side of up to 1440 px.

How to call Enhance Video 1.0 via API

curl https://jantaris.com/v1/generate?wait=60 \
  -H "Authorization: Bearer $JANTARIS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "enhance-video-1.0",
  "input": {
    "resolution": "1080p",
    "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": "enhance-video-1.0",
    "input": {
        "resolution": "1080p",
        "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": "enhance-video-1.0",
    "input": {
      "resolution": "1080p",
      "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));

Parameters

The same schema is available from GET /v1/models/enhance-video-1.0.