Google Lens Search: Reverse Image Finder & OCR

Extract visual matches, AI-generated descriptions, related links, and related searches from any image using Google Lens. Optionally includes OCR text extraction with word-level bounding boxes.

Four search modes give you complete control: scan a single tab for visual or exact duplicates, get the full results page, or run a complete extraction across all tabs in parallel with fast OCR.

---

What can you do with it?

• I am a copyright manager looking to monitor where my unique images, brand photos, or catalog designs are hosted across the web to protect intellectual property.
• I am a retail reseller looking to reverse-search product photos to find exact matching listings, competitor pricing models, and alternative retail hubs.
• I am an AI developer building a multi-modal agent and looking to extract rich, AI-generated descriptions of any photo unblocked.

---

How to reverse-search images step-by-step

1. Create a free Apify account.
2. Open the Google Lens Search in the Apify Store.
3. Enter your target Image URL (e.g. any public JPEG, PNG, or WebP link).
4. Select your desired search mode (e.g. All results, Visual matches, or Exact duplicates).
5. Click Start and download your structured reverse-search dataset as JSON, CSV, or Excel.

---

Input

Field	Type	Required	Description
imageUrl	string	No	Public image URL to search. Either imageUrl or imageUrls must be provided.
imageUrls	array of URLs	No	Paste multiple image URLs to search in a single bulk-batch run.
searchType	enum	No	Controls which type of results to return: all (description, links, searches), visual_matches (visually similar images), exact_matches (exact duplicates), ocr_only (fastest text extraction).
includeAllTabs	boolean	No	When enabled in All results mode, also navigates the Visual matches and Exact matches tabs for more comprehensive results.
includeOcr	boolean	No	Extract text from the image using Google Lens OCR protobuf engine. Runs in parallel, adding zero extra browser execution time.
language	string	No	ISO 639-1 language code for localized search and OCR results (e.g. en, ja, ar).
countryCode	enum	No	Country for proxy geolocation and result localization. Can affect which visual matches and related links are returned.
maxResults	integer	No	Maximum number of visual matches and related links to return.
proxyConfiguration	object	Yes	Proxy settings. Pre-configured residential proxies are required for browser modes to bypass security gates.

---

Output

Each run produces one result with these fields. When includeOcr is enabled, the result also contains the full OCR text block and absolute bounding boxes in parallel.

{
  "imageUrl": "https://images.unsplash.com/photo-1502602898657-3e91760cbb34?w=640",
  "searchType": "all",
  "searchUrl": "https://www.google.com/search?vsrid=CIicteuihfq71QEQ...",
  "aiDescription": "This image shows the Eiffel Tower in Paris, France, along the River Seine.",
  "visualMatches": [
    {
      "title": "The Most Romantic Hotels in Paris with views of the Eiffel Tower",
      "link": "https://www.worldexclusivegroup.com/hotels/the-most-romantic-hotels-in-paris-with-views-of-the-eiffel-tower",
      "source": "",
      "thumbnail": "data:image/png;base64,..."
    }
  ],
  "relatedLinks": [
    {
      "title": "Facts about France",
      "link": "https://the-travelling-twins.com/facts-about-france/",
      "source": "",
      "thumbnail": ""
    }
  ],
  "relatedSearches": ["Eiffel Tower"],
  "scrapedAt": "2026-06-15T11:14:58.726Z"
}

Field reference

Field	Type	Description
imageUrl	string	Public URL of the parsed image.
searchType	string	Configured search mode.
searchUrl	string	Direct link to the Google Search results portal.
aiDescription	string	AI-generated summary of the image content.
visualMatches	array	Pages containing visually similar images with titles, links, and base64 thumbnails.
relatedLinks	array	Broader web pages and references related to the image subject.
relatedSearches	array	Suggested search keywords based on the image subject.
tabs	array	Available categories and result channels Google identified.
ocr	object	Extracted text and bounding boxes (included when includeOcr is true).
scrapedAt	string	ISO timestamp of when the search was executed.

---

Pricing and cost

Pricing is pay-per-result and is billed per successfully processed image search. Failed runs cost absolutely nothing.

• Rate: $7.99 per 1,000 images ($0.00799 per image).
• 100 searches typically cost $0.79.
• 1,000 searches cost exactly $7.99.
• 10,000 searches cost exactly $79.90.
• No fixed monthly subscriptions or hidden fees.

---

Tips and best practices

• Filter by Country. Results can vary significantly depending on proxy geolocation. Set the countryCode parameter to your target market (e.g. DE for Germany) to get localized visual matching indexes.
• Leverage OCR in parallel. If you need both visual matches and text extraction, enable includeOcr. This runs the direct Protobuf OCR engine in parallel, adding zero extra browser execution duration.

---

FAQ

Does it require residential proxies?

Yes. Google immediately blocks public datacenter IPs with Captcha gates on visual search queries. The Actor pre-selects Apify Residential Proxies by default to guarantee reliable unblocked execution.

What image formats are supported?

The Actor supports JPEG, PNG, and WebP formats.

Is this legal?

Yes. The Actor extracts publicly available search results matching what any human would see in a browser. It does not require login, bypass authentication walls, or access private directories.

---

Target SEO keywords

• Google Lens Search API
• reverse image search unblocked
• find image duplicate copies
• Google visual matching API
• AI image description generator

---

Disclaimers and support

• Disclaimer: This Actor is an independent reverse-engineering tool and is not affiliated with, endorsed by, or sponsored by Google LLC or Alphabet Inc.
• Support: Open an issue from the Actor page in the Apify Console for bug reports or feature requests.