Collectors · Search engines

Reverse image search API in Python

Find the pages that use a given image — title, page URL, site and full-size image. One POST from Python with image_url, rows back as JSON with 8 fields, $0.004 per delivered match. No proxies or parsers to maintain.

Get an API key See the collector

A Python requests snippet that posts image_url to the google_lens collector, a line-drawn page titled Reverse image search, and a white card with the fields title, source, domain and description, at $0.004 per match ($4.00 per 1,000). — A Python requests call to the google_lens collector returns one dict per match, at $0.004 each.

First call

Install, call, read the rows.

pip install requests

The only dependency.

import os, requests

r = requests.post(
    "https://api.quanticdata.io/v1/scraper/collectors/google_lens/run",
    headers={"Authorization": f"Bearer {os.environ['QD_API_KEY']}"},
    json={
        "image_url": "https://www.gstatic.com/webp/gallery/1.jpg",
        "max_results": 20,
    },
    timeout=120,
)
r.raise_for_status()
run = r.json()["payload"]
print(run["count"], "rows,", run["cost"]["usd"], "USD")
for row in run["results"]:
    print(row.get("title"), row.get("link"), row.get("source"), row.get("domain"))

Python: one Reverse image search run (Pages using an image), printing title, link, source, domain

The key comes from an environment variable, never from the code. The run answers in the same request when it finishes in time; payload.results holds the rows and payload.cost what they cost.

Request parameters

What the collector takes.

Input of the Reverse image search collector
Parameter	Type	Required	Meaning
`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 (default 20)	How many matches to deliver at most (1–40). You pay only for delivered matches.

Response fields

8 fields per match.

Fields of each row (match)
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.

Add ?format=csv to the runs endpoint to get the same rows as CSV.

Long runs

Run in the background, then poll.

A run that needs more time can go to the background: send "async": true, get 202 with the run id, and poll the runs endpoint until the status is done. Reading a run is free.

import os, time, requests

H = {"Authorization": f"Bearer {os.environ['QD_API_KEY']}"}
r = requests.post("https://api.quanticdata.io/v1/scraper/collectors/google_lens/run", headers=H,
                  json={**{"image_url":"https://www.gstatic.com/webp/gallery/1.jpg","max_results":20}, "async": True}, timeout=30)
run_id = r.json()["payload"]["run_id"]
while True:
    run = requests.get(f"https://api.quanticdata.io/v1/scraper/collectors/runs/{run_id}", headers=H, timeout=30).json()["payload"]
    if run["status"] in ("done", "failed"):
        break
    time.sleep(5)
print(run["status"], run["count"])

Python: background run and polling

Errors

What can come back, and what is billed.

Collector run errors
Status	Meaning	Billed
`400`	The input does not match the collector (`payload.errors`)	No
`401`	Missing or wrong API key	No
`402`	Balance and free credit do not cover the run: top up	No
`422`	The input can never resolve; retrying the same input cannot help	No
`424`	The run failed at the source (blocked, timed out, layout changed); safe to retry	No
`429`	Rate limit or a per-account brake; wait for `Retry-After`	No

Only delivered rows are billed: a run that delivers nothing costs nothing.

Price

$0.004 per delivered match.

What Reverse image search rows cost at list price
Rows	Cost
1	$0.004
1,000	$4.00
10,000	$40.00

Up to 40 matches per run; split larger jobs into several runs. The $2 free credit every month covers about 500 matches. No subscription; paid tiers lower the unit price. All collector prices: collector pricing.

Before you run it

Questions developers ask

Is there a free Reverse image search API?

Every account gets $2 of free usage each month, about 500 matches of this collector at $0.004 each, with no card.

Do I have to handle proxies, retries or blocks?

No. The collector runs on our network and handles them; a run blocked at the source returns 424 and is not billed.

How many rows can one run return?

Up to 40 matches per run (the max_results input, where the collector has one).

Can an AI agent run it?

Yes: the MCP server exposes it as the run_collector tool, with the same input and price. See the MCP server.

Run it on the free credit.

Create an API key, export it as QD_API_KEY and run the example. $0.004 per delivered match, no subscription.

Get an API key Reverse image search API