Reverse image search API

Search engines · v2.2.0 · google_lens

$0.004 / match

$4.00 / 1K · pay per delivered match

A reverse image search API: give it a public image URL — the file, or the page that shows it — and get back where that image appears across the web as rows: title, the page it lives on, source site and domain, plus the full-size image URL. Billed per match delivered, with a 10-match floor per run that finds anything.

By Aldo Morese, founder of QuanticData · Published Aug 21, 2026 · Updated Sep 6, 2026

Run in dashboard See the request

$0.004 per delivered match · $2 free every month · Failed runs never billed

What it does

What a reverse image search API does

Point it at an image and it returns the pages using that picture or ones visually close to it, each with the hosting page and its domain so a match is something you can act on, not just look at. The service downloads the image itself through a residential exit and uploads it to the index directly: hosts that refuse automated fetches (news CDNs, Wikimedia, Pexels) still work, and a viewer page pasted instead of the file — an ibb.co or tmpfiles.org link, a product page — is resolved to its image through og:image.

Doing this yourself means fetching the image, driving a search engine's image upload and parsing a result page that changes without notice. The collector runs that pipeline service-side and returns parsed rows. Note what it is not: it does not read text out of the picture (that is OCR) and it does not return the publish date or pixel size of each match — the index behind it does not expose them.

Inputs

The whole request. Anything you leave out falls back to the default shown in the catalog.

Input	Type	Required	What it does
`image_url`	string	yes	Public http(s) link to the image — the file itself, or a page whose og:image is the picture (ibb.co, tmpfiles.org, a product or news page). No login walls; up to 12 MB.
`country`	string	no	ISO 3166-1 alpha-2 code — proxy exit geo and Google locale (gl). Omit for the default pool.
`lang`	string	no	Interface language (hl), e.g. en, it, de.
`max_results`	integer	no	How many matches to deliver at most (1–40). You pay only for delivered matches.

Outputs — 8 fields, one row per match

What one match looks like

Every delivered match carries these fields. Nullable means the source did not publish it — the field stays empty instead of being guessed.

Field	Type	What it holds
`rank`	integer	1-based position.
`title`	string · nullable	Match title.
`link`	string · nullable	Page the matching image lives on.
`source`	string · nullable	Site name shown on the card.
`domain`	string · nullable	Registrable host of the source page.
`image`	string · nullable	Full-size image URL when exposed.
`thumbnail`	string · nullable	Thumbnail of the matching image, when the publisher hosts one.
`description`	string · nullable	Snippet shown next to the match.

Integration

One POST, typed rows

Base URL https://api.quanticdata.io/v1, Bearer auth, the same key as every other Data API. Endpoint: POST /v1/scraper/collectors/google_lens/run.

curl -X POST https://api.quanticdata.io/v1/scraper/collectors/google_lens/run \
  -H "Authorization: Bearer $QD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"image_url":"https://www.gstatic.com/webp/gallery/1.jpg","max_results":20}'

import requests

r = requests.post(
    "https://api.quanticdata.io/v1/scraper/collectors/google_lens/run",
    headers={"Authorization": f"Bearer {QD_API_KEY}"},
    json={
        "image_url": "https://www.gstatic.com/webp/gallery/1.jpg",
        "max_results": 20
    },
    timeout=120,
)
for row in r.json()["payload"]["results"]:
    print(row)

const res = await fetch(
  "https://api.quanticdata.io/v1/scraper/collectors/google_lens/run",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.QD_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({"image_url":"https://www.gstatic.com/webp/gallery/1.jpg","max_results":20}),
  },
);
const { payload } = await res.json();
console.table(payload.results);

claude mcp add quanticdata \
  -e QUANTICDATA_API_KEY=qd_live_your_key_here \
  -- npx -y quanticdata-mcp

# then, in the chat:
> run the google_lens collector with image_url="https://www.gstatic.com/webp/gallery/1.jpg" and max_results=20

Example response

POST /v1/scraper/collectors/google_lens/run

$ curl $QD/google_lens/run \
    -H "Authorization: Bearer $QD_API_KEY" \
    -d '{"image_url": "https: //www.gstatic.com/webp/gallery/1.jpg", "max_results": 20}'
{ "status": "done", "count": 20,
  "results": [
    {
      "title": "…",
      "link": "…",
      "source": "…",
      "domain": "…" } ],
  "cost": 0.08 }
# 20 matches × $0.004 · nothing delivered, nothing charged

Try it

Reverse image search, running now

Change the input and run it against the live collector — nothing to install, no sign-up.

Run it from your own code, on your own inputs

Same collector, same rows — $2 of free API credit every month, no card.

Get my free API key

Reverse image search API: from image_url, QuanticData reads the visual matches and returns one row per match with title, domain and description, at $0.004 per delivered match. — You send image_url and country; the run goes out through a residential exit and comes back as matches with rank, title and source — 8 fields on every row — and you are billed $0.004 for each match actually delivered, nothing for a run that delivers none.

$0.004 / match500 matches on the free $2 every month

Semantic inputimage_url, country, lang — no URL lists

Up to 40matches per run, pagination handled for you

No browserread over HTTP/TLS — cheaper and faster than rendering

Pricing

Reverse image search API pricing

$0.004 per delivered match. A run that delivers nothing costs nothing: blocked pages, challenges and retries are on us, and the $2 monthly allowance covers about 500 matches before you spend anything.

$0.004per delivered match$4 per 500 delivered matches

500 matcheson the free allowance$2 every month, no card

Zero rowszero chargeblocks, captchas and retries are on us

−30%on volume tiersthe catalog returns your key's price

Pay as you go

$0/mo

$2 free credit / month
60 requests / min
List unit prices

Starter

$19/mo

$15 free credit / month
300 requests / min
10% off unit prices

Growth

$79/mo

$50 free credit / month
600 requests / min
20% off unit prices

Scale

$299/mo

$250 free credit / month
1,200 requests / min
30% off unit prices

Same wallet, same key and same $2 monthly allowance as every other Data API. Prices are launch pricing read live from the billing config — GET /v1/scraper/collectors returns the price your key actually pays.

What people build with the reverse image search API

Three shapes of work this endpoint was designed around.

Brand and asset protection

Run your product shots through it to find every page reusing them, with the hosting domain to prioritise takedowns.

Counterfeit and leak detection

Track where a hero image surfaces across marketplaces and domains you never licensed.

Image provenance

Given a photo, list the pages carrying it and their sources before you trust or attribute it.

Reverse image search API versus rolling your own

The differences that actually cost time when you build this in-house.

	DIY scraper	This collector
What you send	An image and a search engine to fight with	A public image URL, or the page that shows it
Hotlink-protected hosts	Your fetch is refused, so is the engine's	Fetched through a residential exit and uploaded directly
Each match	A thumbnail with no context	The hosting page, its domain and the source

What people search for

Live autocomplete demand around Reverse image search, pulled with our own Keyword ideas collector.

Reverse image search API: the POST to the google_lens collector, 20 matches delivered and the bill, 20 × $0.004 = $0.08 in usage.cost_usd; zero matches would cost $0. — The same call you would paste into a terminal: a Bearer key, image_url, country and lang in the body, and back the envelope every QuanticData endpoint returns — type, message, payload — where count is how many matches arrived and usage.cost_usd is $0.08, which is 20 × $0.004. A run that delivers nothing costs nothing. The key is good for 60 req/min on the free tier.

Sources and standards

The platform documentation and standards this collector is built against — check any claim on this page against the primary source:

IPTC: Photo Metadata Standard

FAQ

Questions we get about the reverse image search API.

Something else? Ask us

Does it use Google Lens?

No. Google now renders Lens results only in the browser, so no request-based API can read them. The collector reads a reverse-image index that serves its results server-side: pages that contain the image, with title, link, domain and the full-size picture. Visually similar pages are included; exact-use-only filtering is not available.

Can it read text from the image (OCR)?

No. This returns where the image appears — matching pages and their sources — not the text inside it. Pulling the words out of a picture is OCR, a different task from reverse image search.

Does the image have to be public?

Yes, reachable over http(s) without a login, up to 12 MB. You can pass either the direct link to the file or the page that displays it: the service reads the page's og:image. A file on your laptop needs to be hosted somewhere first.

What do I pay when a run finds only a few matches?

Each run that finds anything is billed for at least 10 matches, because the work — fetching the image, uploading it, reading the index — is the same for 3 matches as for 40. A run that finds nothing costs nothing, and an unreachable image is refused with the reason before any search happens.

Is there a free reverse image search API?

Every account gets $2 of credit every month with no card, which is about 500 delivered matches on this endpoint at $0.004 each. It renews monthly, and a run that delivers nothing is never billed — so a failed or blocked attempt does not eat the allowance.

How much does one run cost?

Multiply the rows you actually receive by $0.004. A run capped at 40 matches — the maximum for this collector — costs $0.16 if every row comes back, and less when the source has fewer. Volume tiers take up to 30% off, and GET /v1/scraper/collectors returns the price your key actually pays.

Run the reverse image search API now

$2 of free credit every month, no card. Your key returns its own prices from GET /v1/scraper/collectors.

Run in dashboard

Illustration: three coloured zones of the page that is read (Visual matches) turn into clean JSON with the fields title, domain and description; 8 fields on every row.