Topaz API
Topaz API on WaveSpeedAI — 17 Topaz Labs image and video enhancement endpoints over REST: image upscaling to 8K with Standard, Wonder and Bloom models, sharpen, denoise, restore and lighting fixes, and video upscaling with Proteus, Starlight and Astra, plus denoise, deblur, SDR-to-HDR, colorization and frame interpolation.
Send an image or a video and get back an enhanced version: upscale photos to 2K, 4K or 8K, restore soft, noisy or damaged images, and upscale, denoise, deblur, colorize, convert to HDR or raise the frame rate of video. Every endpoint runs on the same REST prediction flow as every other model on WaveSpeedAI, priced by the size of the output.
Overview
About the Topaz API
What Topaz does, how it fits in the Topaz Labs model lineup, and why teams reach for it.
Topaz is a super-resolution and enhancement model from Topaz Labs, available through the WaveSpeedAI REST API. Topaz API on WaveSpeedAI — 17 Topaz Labs image and video enhancement endpoints over REST: image upscaling to 8K with Standard, Wonder and Bloom models, sharpen, denoise, restore and lighting fixes, and video upscaling with Proteus, Starlight and Astra, plus denoise, deblur, SDR-to-HDR, colorization and frame interpolation.
Send an image or a video and get back an enhanced version: upscale photos to 2K, 4K or 8K, restore soft, noisy or damaged images, and upscale, denoise, deblur, colorize, convert to HDR or raise the frame rate of video. Every endpoint runs on the same REST prediction flow as every other model on WaveSpeedAI, priced by the size of the output.
The Topaz family on WaveSpeedAI ships 17 REST endpoints covering Video-Tools, Upscale-Video, Upscale-Image, Image-Tools workflows. Each variant carries its own pricing, parameter knobs, and example outputs — pick the one that matches your input modality and production constraints, or call several from the same API key to compose multi-step pipelines.
Run Topaz through the same API key, billing account, and rate-limit envelope you use for the other 1,000+ AI models on WaveSpeedAI. No separate vendor setup, no per-provider SDKs, no per-vendor rate-limit envelopes — one integration covers everything from text-to-image and text-to-video through audio synthesis, 3D generation, upscaling, and editing.
Specs
Topaz API capabilities and release status
The model-specific details developers search for before choosing an API: availability, expected output length, reference support, and the current live fallback.
Endpoints
9 image, 8 video
topaz/image/ covers upscaling (precision, generative, creative and transparent PNG), sharpen, generative denoise, restore and lighting; topaz/video/ covers upscaling (precision, Starlight generative, Astra creative), denoise, deblur, HDR, colorization and frame interpolation.
Image upscale
2K, 4K, 8K
target_resolution sets the output area (about 4, 16.8 or 67 megapixels) and the source aspect ratio is kept.
Video
Up to 4K, 5 minutes
Upscalers take a target_resolution of 720p, 1080p, 2K or 4K; the other video endpoints take a resolution. Video is processed at up to 30 fps and up to 300 seconds.
Pricing
By output size
Images are priced by output megapixels and video by output resolution and seconds, so a small job costs a small amount.
Endpoints
All Topaz API endpoints
17 Topaz endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.
/filters:quality(82)/media/images/b0be9d42-7d1d-4b04-9864-915f6fb480d7.webp)
Video Deblur
Topaz Video Motion Deblur removes motion blur from fast-moving footage using Topaz Themis, restoring sharper detail and clearer frames for sports, action footage, handheld video, archival restoration, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/754500ad-c3c9-49df-a122-239db631c28c.webp)
Video Colorize
Topaz Video Colorization restores natural color to black-and-white and monochrome footage while preserving the original scene, subjects, framing, and motion for archival restoration, documentary footage, old videos, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/bf1f775a-ed38-4034-8ff0-e2e9154c8b15.webp)
Video Hdr
Topaz Video SDR to HDR converts SDR footage into 10-bit HDR video with Topaz Hyperion, enhancing dynamic range, highlight detail, and overall visual depth for cinematic, archival, streaming, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/00f2ee33-e55f-4002-ad1f-4ccda30110f3.webp)
Video Frame Interpolation
Topaz Video Frame Interpolation increases video frame rates and creates smooth slow motion using Topaz Apollo, Chronos, and Aion models, making it suitable for sports footage, cinematic slow motion, animation, restoration, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/c3ce567f-3648-4679-8ea6-5e8c33593e78.webp)
Video Denoise
Topaz Video Denoise removes noise and grain from video while preserving natural texture, fine detail, and overall image quality for low-light footage, compressed video, archival restoration, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/77793176-eacd-4ce6-aa69-14cfa4bc3e33.webp)
Video Upscale Creative
Topaz Video Upscale Creative enhances AI-generated videos with Topaz Astra, creatively reconstructing and adding new visual detail for generative video, cinematic content, social media, advertising, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/043063a5-3758-49de-ab1d-64db061ede34.webp)
Video Upscale Generative
Topaz Video Upscale Generative restores and upscales real and AI-generated videos with Topaz Starlight diffusion models, reconstructing detail and improving visual quality for low-resolution footage, generative video, restoration, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/5465f49c-e73d-4e77-ac6d-c25c80e027fc.webp)
Video Upscale
Topaz Video Upscale upscales and enhances video up to 4K with Topaz's precision Proteus, Artemis, Gaia, Theia, Iris and Dione models. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/0b6fa62d-b057-4e25-b85a-3df860344788.webp)
Image Transparent Upscale
Topaz Transparent Image Upscale enlarges transparent PNG images while preserving the alpha channel, clean edges, and transparency for logos, product assets, graphics, design elements, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/bcdd00ed-3a1d-4088-b597-94934cbe1040.webp)
Image Upscale Creative
Topaz Image Upscale Creative enhances AI-generated images with Topaz Bloom, creatively reconstructing and adding new visual detail for concept art, marketing visuals, creative assets, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/9c25742f-c0e5-43c3-8d7b-819c1bd4186a.webp)
Image Upscale Generative
Topaz Image Upscale Generative upscales and restores images with Topaz Wonder, Recover, and Redefine models, improving resolution, reconstructing detail, and repairing low-quality imagery for creative assets, photography, design, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/09040d45-11a5-448d-81cd-dece42e5d774.webp)
Image Upscale
Topaz Image Upscale enlarges photos and images to 2K, 4K, or 8K using precise, non-generative Topaz upscaling models, preserving original visual content while improving resolution and clarity for photography, product images, creative assets, and production workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/138fb1af-fdbc-41ee-9c7d-993b2bf0e09e.webp)
Image Denoise Generative
Topaz Image Denoise Max removes heavy noise and reconstructs lost detail with the generative Topaz Denoise Max model, making it suitable for low-light photography, compressed images, photo restoration, and professional image enhancement workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/a1b790e2-49e6-424f-8eb3-3e2398290e22.webp)
Image Sharpen Generative
Topaz Image Sharpen Generative restores severely blurred images with generative Topaz Super Focus models, rebuilding lost detail and improving clarity for photography, image restoration, creative assets, and professional enhancement workflows. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408112327_sqr1uegu.webp)
Image Sharpen
Topaz Image Sharpen sharpens soft, out-of-focus and motion-blurred photos while keeping them natural. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/0537a2db-382b-4665-8bce-133a639f3b85.webp)
Image Restore
Topaz Image Restore cleans dust, scratches and blemishes from scans and old photos. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408112304_igpft99n.webp)
Image Lighting
Topaz Image Lighting fixes exposure and white balance, colorizes black-and-white photos and converts to HDR. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Examples
See Topaz in action
Real outputs generated by the Topaz API. Hover any video to preview, click to open the full-size viewer.
How to
How to use the Topaz API
Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.
- 01
Get an API key
Sign up for a WaveSpeedAI account and copy your API key from the dashboard. New accounts come with free starter credits — enough to run the playground a few dozen times before billing kicks in.
- 02
Submit a prediction
POST your input as JSON to https://api.wavespeed.ai/api/v3/topaz/image/upscale. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.
- 03
Poll for completion
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result. Return outputs on completed; stop with an error on failed, cancelled, timeout, or deleted; continue polling for every other status.
- 04
Read the output URL
Once status is "completed", read the URL from data.outputs[0]. The URL points to your generated media on the WaveSpeedAI CDN — image, video, audio, or 3D file depending on the Topaz variant you called.
Use cases
What you can build with Topaz
Common workflows developers and creators use the Topaz API for.
Upscale photos for print and e-commerce
topaz/image/upscale enlarges photos to 4K or 8K while keeping real detail; topaz/image/upscale-generative rebuilds detail in low-resolution or heavily compressed images.
Upscale AI-generated images and video
Bloom (topaz/image/upscale-creative) and Astra (topaz/video/upscale-creative) add new, reimagined detail to AI-generated images and clips, steered by an optional prompt.
Restore old and low-quality footage
Starlight (topaz/video/upscale-generative) restores and upscales low-resolution, compressed or archival video; topaz/video/upscale handles deinterlacing, haloing and everyday upscales.
Fix blur, noise and damage
Sharpen and Denoise rescue soft and grainy photos, Restore removes dust and scratches from scans, and the video Denoise and Deblur endpoints clean up low-light and fast-moving footage.
Smooth slow motion and higher frame rates
topaz/video/frame-interpolation converts footage to 48, 50, 60 or 120 fps, or slows it down 2x to 8x with Apollo, Chronos or Aion.
HDR and color for old video
topaz/video/hdr turns SDR footage into 10-bit HDR, and topaz/video/colorize adds natural color to black-and-white video.
Tips
Tips for prompting Topaz
Practical advice for getting better outputs from Topaz — drawn from the patterns that work across upscaler models in production pipelines.
- 01
Pick the upscaler by source
Use the precision upscalers (Standard V2, Proteus) for clean photos and footage, the generative ones (Wonder, Starlight) for low-resolution or compressed sources, and the creative ones (Bloom, Astra) for AI-generated content.
- 02
Fix noise before sharpening
When a photo is both noisy and soft, run Denoise first and Sharpen second. Sharpening a noisy image makes the grain stronger along with the detail.
- 03
Try a short clip first
Video is priced by output resolution and seconds. Run a few seconds at 1080p to choose the model, then process the full clip or go up to 4K.
- 04
Keep PNG for multi-step pipelines
Set output_format to png when the result goes into another step such as a second fix, so each pass does not add JPEG compression.
Pricing
Topaz API pricing
Pricing is per-output. The final charge scales with the parameters you set in each variant's playground (resolution, duration, output count, references).
| Endpoint | Type | Starting price |
|---|---|---|
| topaz/ | video-tools | $0.10 |
| topaz/ | video-tools | $0.10 |
| topaz/ | video-tools | $0.10 |
| topaz/ | video-tools | $0.10 |
| topaz/ | video-tools | $0.10 |
| topaz/ | upscale-video | $0.10 |
| topaz/ | upscale-video | $0.10 |
| topaz/ | upscale-video | $0.10 |
| topaz/ | upscale-image | $0.10 |
| topaz/ | upscale-image | $0.10 |
| topaz/ | upscale-image | $0.10 |
| topaz/ | upscale-image | $0.10 |
| topaz/ | image-tools | $0.10 |
| topaz/ | image-tools | $0.10 |
| topaz/ | image-tools | $0.10 |
| topaz/ | image-tools | $0.10 |
| topaz/ | image-tools | $0.10 |
API
Call the Topaz API
Sign up for an API key at wavespeed.ai/accesskey, then submit a prediction via REST. The playground generates ready-to-paste samples for any combination of inputs.
POSThttps://api.wavespeed.ai/api/v3/topaz/image/upscale
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/topaz/image/upscale" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"model": "Standard V2",
"target_resolution": "4k",
"output_format": "jpeg"
}')
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/topaz/image/upscale";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"model": "Standard V2",
"target_resolution": "4k",
"output_format": "jpeg"
}),
});
const task = body.data ?? body;
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"model": "Standard V2",
"target_resolution": "4k",
"output_format": "jpeg"
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/topaz/image/upscale", json.dumps(payload).encode())
task = body.get("data", body)
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Compare
Topaz vs alternatives
When to pick Topaz over similar models on WaveSpeedAI.
Topaz vs Topaz desktop apps
Topaz Gigapixel, Photo AI and Video AI run on your own computer. The Topaz API endpoints run in the cloud over REST, which suits servers, batch jobs and apps that process media for their own users, with no GPU to manage.
Topaz vs Other upscalers on WaveSpeedAI
WaveSpeedAI also hosts its own image and video upscalers. The Topaz endpoints add the Topaz model families (Wonder, Bloom, Proteus, Starlight, Astra) and dedicated fixes such as deinterlacing, HDR and colorization.
Topaz vs Self-hosted open-source models
Open-source upscaling and restoration models need your own GPUs and maintenance. The Topaz endpoints are hosted, priced by output size, and share one API key and billing account with every other model on WaveSpeedAI.
FAQ
Topaz API — Frequently asked questions
Pricing, license, integration — common questions about running Topaz on WaveSpeedAI.
Which Topaz models are available on WaveSpeedAI?
Nine image endpoints (upscale, generative upscale, creative upscale, transparent upscale, sharpen, generative sharpen, generative denoise, restore and lighting) and eight video endpoints (upscale, Starlight generative upscale, Astra creative upscale, denoise, deblur, HDR, colorize and frame interpolation). Every live endpoint is listed on this page with its current price.
How long can a video be?
Up to 300 seconds, processed at up to 30 fps. Colorization takes up to 15 seconds.
How are Topaz endpoints priced?
Images are priced by output megapixels and video by output resolution and length, at the price shown on each model page. WaveSpeedAI is pay as you go: no subscription, and credits never expire.
What is the Topaz API?
Topaz is a Topaz Labs upscaler model exposed as a REST API on WaveSpeedAI. Topaz API on WaveSpeedAI — 17 Topaz Labs image and video enhancement endpoints over REST: image upscaling to 8K with Standard, Wonder and Bloom models, sharpen, denoise, restore and lighting fixes, and video upscaling with Proteus, Starlight and Astra, plus denoise, deblur, SDR-to-HDR, colorization and frame interpolation. You can call it programmatically or try it from the playground linked above.
How do I call the Topaz API?
Sign up for a WaveSpeedAI account, copy your API key from /accesskey, then POST to https://api.wavespeed.ai/api/v3/topaz/image/upscale with your input as JSON. The endpoint returns a prediction id. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. Production-oriented Python / Node.js / cURL examples are above.
How much does the Topaz API cost?
Topaz starts at $0.10. The exact cost scales with the parameters you set (resolution, duration, output count, references). The live cost preview next to the Generate button in the playground shows the exact price for your current input.
Which Topaz variants are available?
WaveSpeedAI hosts 17 live Topaz endpoints: topaz/video/deblur, topaz/video/colorize, topaz/video/hdr, topaz/video/frame-interpolation, topaz/video/denoise, topaz/video/upscale-creative, topaz/video/upscale-generative, topaz/video/upscale, and more. Each variant has its own playground page and pricing.
Can I use Topaz outputs commercially?
Commercial usage rights follow the Topaz Labs model license. Most Topaz Labs models permit commercial output use; see each model's playground page for the specific license summary, and WaveSpeedAI's Terms of Service for platform-level conditions.
Why use Topaz on WaveSpeedAI instead of going direct?
One API key + one billing account across Topaz AND 1,000+ other AI models from other providers. No per-vendor SDK setup, no separate rate-limit envelopes, no rewrite-per-vendor integration code. Pricing is typically at parity with or below Topaz Labs's direct API.
Provider
About Topaz Labs
The team behind Topaz and the broader Topaz Labs model lineup on WaveSpeedAI.
Topaz Labs makes AI image and video enhancement software used by photographers, filmmakers and studios, known for Gigapixel, Photo AI and Video AI. Its models focus on upscaling and recovering real detail: sharpening, noise reduction, restoration, lighting, HDR and frame interpolation. On WaveSpeedAI the Topaz models are available as REST endpoints with one API key and pay-as-you-go pricing.
Start building with Topaz on WaveSpeedAI
Free starter credits on signup. One API key across 1,000+ AI models from Topaz Labs and every other provider.