Topaz Labs models API

Call 1 Topaz Labs models through one PopNow API key: Topaz Denoise & Sharpen. Prices start at $0.12 per image.

models: 1
endpoints: 1
starting price, per image: $0.12

Topaz Labs models

Topaz Denoise & Sharpentopaz/denoise-sharpen/editNewRemove noise or fix blur at the same resolution, up to 24 MPImageFrom$0.12per image

Choosing Topaz Labs for photo denoise and sharpening

One endpoint, two families of presets

Topaz Denoise & Sharpen is a single image task with one required choice: the preset. Every preset that starts with denoise_ removes noise and grain at three strengths, normal, strong and extreme. Every preset that starts with sharpen_ repairs blur, either generally (standard, strong, natural) or for a specific cause such as a portrait, wildlife, a missed focus point, camera shake or a soft lens. The model works on the photo you send and does not invent a new scene, so it fits late in a pipeline: after capture or generation, before export. Price is a flat per-image rate, so the cost of a batch is known before the first request leaves your backend.

Pick the preset from the defect, not from a quality ladder

Start by naming what is wrong with the frame. High ISO speckle, compression blocks and colour grain belong to the denoise presets; begin with denoise_normal and only step up when residual texture is still visible at full size, because the stronger settings smooth fine detail such as hair, fabric weave and skin pores along with the noise. Blur belongs to the sharpen presets. A face that is slightly soft calls for sharpen_portrait, a subject smeared sideways by movement calls for sharpen_motion_blur, and a frame where the background is sharp but the subject is not calls for sharpen_refocus. Running a sharpen preset on a noisy file tends to amplify the grain, so when a photo has both problems, run denoise first and sharpen the cleaned result in a second request.

Keep inputs, presets and outputs together

Send the photo as image_url from your backend with an Authorization Bearer header carrying a sk-popnow- key, and use the full public call name from the task reference in /api/v1/jobs/createTask. Inputs can be JPEG, PNG or WebP up to 24 megapixels, and the result keeps the original resolution, so the step does not change your layout or crop. Choose output_format png when the image will be edited again and jpeg for delivery. Store the taskId, the source URL and the preset with the output; when a reviewer prefers a softer or stronger pass, you can rerun only that file with a neighbouring preset instead of repeating the whole batch. Poll /api/v1/jobs/recordInfo or verify a completion webhook before you replace the original asset.

Topaz Labs API prices

See pricing

Model	Best for	List price	PopNow price	You save
Topaz Denoise & Sharpen`topaz/denoise-sharpen/edit`	Image Denoiser	—	$0.12per image

List prices are each maker's own published price for the same output, checked on Oct 14, 2026. Prices shown are starting prices; open a model for every tier.

Call a Topaz Labs model

The same request works for every model: change the model name and its input.

curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "topaz/denoise-sharpen/edit",
  "input": {
    "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
    "preset": "denoise_normal",
    "output_format": "jpeg"
  }
}'

import os, uuid, requests

res = requests.post(
    "https://api.popnow.ai/api/v1/jobs/createTask",
    headers={
        "Authorization": f"Bearer {os.environ['POPNOW_API_KEY']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "model": "topaz/denoise-sharpen/edit",
        "input": {
            "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
            "preset": "denoise_normal",
            "output_format": "jpeg"
        }
    },
    timeout=30,
)
body = res.json()
if body["code"] != 200:
    raise RuntimeError(f'{body["code"]} {body["msg"]}')
print(body["data"]["taskId"])  # poll this id, or wait for your callBackUrl

const res = await fetch("https://api.popnow.ai/api/v1/jobs/createTask", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.POPNOW_API_KEY}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    "model": "topaz/denoise-sharpen/edit",
    "input": {
      "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
      "preset": "denoise_normal",
      "output_format": "jpeg"
    }
  }),
});
const { code, msg, data } = await res.json();
if (code !== 200) throw new Error(`${code} ${msg}`);
console.log(data.taskId); // poll this id, or wait for your callBackUrl

Frequently asked questions

Does Topaz Denoise & Sharpen upscale my photo?

No. The output keeps the input resolution, so a 4000 by 3000 photo returns at 4000 by 3000. Use an upscaling model as a separate step when you need more pixels, and run denoise before the upscale so the larger file does not inherit enlarged grain.

Which denoise strength should I start with?

Start with denoise_normal and inspect the result at 100 percent zoom. Move to strong or extreme only when grain is still visible, because stronger presets also flatten fine texture such as hair, fabric and skin detail that viewers notice in close crops.

Can one request both denoise and sharpen a photo?

Each request runs one preset. For a photo with noise and blur, send it through a denoise preset first, then pass that output to a sharpen preset. Doing it in this order keeps the sharpening step from exaggerating the grain that was already in the file.

How is a Topaz request billed?

Each processed image is charged a flat per-image price that does not depend on the preset, the output format or the photo size within the 24 megapixel limit. The current price appears on the model reference page next to the task schema.

What should I compare before switching providers?

Use the same source photo and judge the full-size crop rather than a thumbnail. Check whether edges gain halos, whether faces stay natural and whether flat areas such as sky stay clean. Image editing models in the catalog can also restore photos but may change content.

Other model makers

All model makers

Start building in minutes

One key for every model, a USD balance you top up when you need to, and an exact price before every run.

Get API key Try in Playground