Reverse Image Search API Built for Provenance and Compliance
Search 82+ Billion indexed images to find out where a picture came from and where else it lives. Multiple search engines run on every call and their results are merged and deduplicated. Each match comes back with the page URL, the matching image URL, and a similarity score, plus a clean list of domains you can act on.
curl -X POST https://app.picdefense.io/api/v2/backlinks \
-H "X-API-TOKEN: USERID:APIKEY" \
-H "Content-Type: application/json" \
-d '{"url": "https://example.com/photo.jpg"}'{
"status": 1,
"message": "succeeded",
"data": {
"backlinks": {
"urls": [{
"url": "https://example.com/article/sample-article",
"similarity_score": 95,
"backlink_image_url": "https://example.com/images/sample.jpg"
}],
"found_at": ["example1.com", "example2.com"],
"image_url": ["https://example1.com/image.jpg"]
}
}
}Pay Per Call. No Subscription.
Buy prepaid credits once and spend them on any PicDefense endpoint.
| Endpoint | Credits / call | Per 1,000 calls |
|---|---|---|
POST /backlinksPages, domains, and image URLs where the image appears. | 0.30 | $21.00 – $60.00 |
Ranges run from the 100,000-credit pack down to the 100-credit pack. Credits are charged only on successful calls and never expire. See all credit packs on the pricing page.
What It Detects
Page-Level Matches
Get the exact pages that use the image, not just a count, so you can review each one.
Similarity Scores
Each match carries a 0 to 100 score so you can separate exact copies from loose look-alikes.
Domain Rollup
found_at groups matches by domain, which is what you need for outreach, takedowns, or reporting.
Edited Copies
Finds resized, recompressed, and cropped versions of the same image, not only byte-identical files.
Built for These Workflows
Where teams wire this endpoint into their pipelines.
Provenance Before Publishing
If an image already appears on stock sites and dozens of domains, it is probably not original. Check before it goes live.
Photographers Tracking Their Work
Monitor where your portfolio is being used and build a list of sites to license or contact.
Demand Letter Evidence
Show how widely an image has circulated and where it first appeared when you assess a copyright claim.
Duplicate and Fraud Checks
Spot recycled listing photos, fake profile pictures, and reused product images across the web.
What You Get Back
Every call returns JSON with status, message, error, and a data object. These are the fields inside data.
POST /backlinks
Pages, domains, and image URLs where the image appears.
| Field | Type | Description |
|---|---|---|
| backlinks.urls[].url | string | Page where the image was found. |
| backlinks.urls[].similarity_score | number | How closely the found image matches yours, from 0 to 100. |
| backlinks.urls[].backlink_image_url | string | Direct URL of the matching image on that page. |
| backlinks.found_at | string[] | Deduplicated list of domains where the image appears. |
| backlinks.image_url | string[] | Every URL where the exact image was found. |
Why Teams Choose the PicDefense Reverse Image Search API
Structured for Action
Domains, page URLs, and image URLs come back as separate lists, ready to drop into a report or queue.
Merged Multi-Engine Results
Each call runs more than one search engine and merges the matches, so you get broader coverage than any single index without extra integrations.
Same Key, More Signals
Need a verdict, not just matches? The Copyright Risk Check API includes these backlinks along with stock, EXIF, and watermark data.
Full and Partial Matches
Returns exact copies and partial matches such as crops, so edited reuse still shows up.
Prefer a Dashboard?
PicDefense can crawl your whole website, find every image, and run reverse search on each one for you.
Explore the Inventory EngineUse It From an AI Agent
Every endpoint is also exposed as a tool on the hosted PicDefense MCP server. Connect Claude, Cursor, or any MCP client with your existing API token.
https://mcp.picdefense.io/mcpMCP setup guidePairs Well With
One API key and one credit balance cover every endpoint.
Copyright Risk Check API
One call returns a high/medium/low copyright risk verdict plus the evidence behind it.
Learn moreWatermark Detection API
Detect visible stock and photographer watermarks and learn which agency they belong to.
Learn moreImage Recognition API
Faces, logos, landmarks, labels, and content safety, organized around what needs a release.
Learn moreFrequently Asked Questions
How is this different from a consumer reverse image search site?
Consumer search sites are built for people clicking through results, not for code. This endpoint returns structured JSON with page URLs, image URLs, domains, and similarity scores that your application can process directly.
What does the similarity score mean?
It is a 0 to 100 measure of how closely the found image matches the one you submitted. Scores near 100 usually indicate the same image, possibly resized or recompressed.
How much does a search cost?
Each successful call uses 0.30 credits, roughly $0.02 to $0.06 per search depending on your credit pack. A search that finds no matches still counts as a successful call.
Can I find where an image was first published?
The API returns where the image appears today. Comparing the domains, especially stock sites and original publishers, is usually the fastest way to trace its likely origin.
Start Calling the Reverse Image Search API Today
Create an account, copy your API token from Settings, and make your first request in minutes.
PicDefense API results are automated, probabilistic signals intended to support your own review. They do not constitute legal advice and do not guarantee that an image is free of third-party rights. Consult a qualified attorney for decisions about copyright, trademark, or publicity rights.