Bing Reverse Image Search 🔍 Similar Images, Pages & OCR

Bing Reverse Image Search takes a picture — an image link or a file you upload — and returns what Bing finds for it: Bing's best guess of what the picture shows, hundreds of visually similar images (full-size URL, size, file type, publish date), the pages that carry the picture, related and shopping searches, any text written in the picture, and an AI description with its sources.

Perfect for photographers and brands tracing where their images are reused, e-commerce and marketplace teams checking product photos, journalists and researchers verifying where a picture came from, and SEO teams looking for backlink and image-credit opportunities — without a Bing account or an API key.

What does Bing Reverse Image Search do?

Give it one picture or a list of hundreds. For each one it returns a summary row and then the results you choose, ready for JSON, CSV or Excel.

• Bing's best guess — the name Bing gives the picture, plus the search it suggests for it.
• Visually similar images — most similar first, each with the full-size image URL, a thumbnail, Bing's own cached copy (still works when the original is taken down), width and height, file size, file type, publish date and the page it sits on. A single picture can return several hundred.
• Pages that carry the picture — the web pages where the picture itself appears, with their titles and dates.
• Related and shopping searches — what people search for with this picture, ready to feed keyword research. Related and shopping searches share your row limit fairly, so a low limit still returns both. For pictures Bing has no picture-based searches for (documents, screenshots), the related searches Bing shows for its best guess are returned instead and marked origin: "web".
• Text in the picture — every line of writing Bing can read, with where it sits on the picture.
• AI description — Bing's short description of the picture with numbered sources.
• Links, files and data links — paste image links, upload a file, or pass a data: link. Large pictures are resized automatically; you never have to prepare them.
• Region and safety — 18 Bing markets and all three SafeSearch levels.

What data can you extract from Bing Reverse Image Search?

Result type	Fields
Picture summary (image_summary)	bestGuess, suggestedQuery, bestRepresentativeQuery, hasText, similarImagesAvailable, the counts returned, textInImage, and the size and type of the picture you supplied
Similar image (similar_image)	title, link, source, original, originalWidth, originalHeight, thumbnail, cachedImage, fileSize, format, datePublished, dateDiscovered, pagesIncludingCount, availableSizesCount, accentColor, imageId, bingUrl
Page that carries the picture (matching_page)	the same fields as a similar image
Related search (related_search)	text, category (related or shopping), origin (image or web), searchUrl, thumbnail
Text in the picture (text)	text, boundingBox (the line's four corners as fractions of the picture)
AI description (ai_overview)	text, citations (number, URL, title, source, snippet)

Values are delivered as Bing gives them: dates keep Bing's format and nothing is rounded or translated. Only fields that carry no information for you (tracking tokens) are left out, and a value Bing did not send is null rather than guessed. Every row also carries searchImage (the picture it belongs to), scrapedAt and _source.

Why use Bing Reverse Image Search on Apify?

Running it on Apify gives you API access, scheduling, monitoring, integrations (Make, Zapier, n8n, webhooks) and proxy rotation without managing infrastructure. One picture with the default settings finishes in about ten seconds; a picture with several hundred similar images takes under a minute.

How to run a reverse image search on Bing

1. Open Bing Reverse Image Search in Apify Console.
2. Paste one or more image links into Image links, or upload a picture file. Use the direct address of the image — right-click the picture and choose Copy image address.
3. Choose What to return. Similar images, pages and related searches are on by default.
4. Set Max results per type. Start small: 50.
5. Click Start and wait for the run to finish.
6. Download the results as JSON, CSV or Excel, or fetch them over the API.

How much does it cost to run a reverse image search on Bing?

You pay for what you receive, in two parts. A picture is charged once, and only when Bing returns something for it; each similar image or page that carries the picture is charged as a match.

Event	FREE	BRONZE	SILVER	GOLD
Picture searched (once per picture; includes the summary, related and shopping searches, text in the picture and the AI description)	$0.0040	$0.0030	$0.0025	$0.0020
Match returned (each similar image or page that carries the picture)	$0.0010	$0.0008	$0.0006	$0.0005

• One picture with the defaults (up to 50 similar images and 50 pages) costs about $0.10 at the highest tier price and $0.05 on GOLD.
• A picture that cannot be loaded, that Bing returns nothing for, or that fails, is never charged. Notices are never charged.
• A match is never delivered or charged twice for a picture.
• Test with a low Max results per type first, and set a maximum cost per run in Apify — the Actor sizes the run to fit it.

Input and output examples

Input

{
    "imageUrls": ["https://www.google.com/images/branding/googlelogo/2x/googlelogo_color_272x92dp.png"],
    "resultTypes": ["similarImages", "pagesWithImage", "relatedSearches", "textInImage", "aiOverview"],
    "maxResults": 50,
    "market": "us",
    "safeSearch": "moderate"
}

Input value	What it does
imageUrls	Image links, one picture each. Duplicates are removed.
imageFile	A picture uploaded from your computer, searched in addition to the links.
resultTypes	Which results to return: similarImages, pagesWithImage, relatedSearches, textInImage, aiOverview.
maxResults	Rows per picture and per result type (not a global total). 0 returns everything Bing has.
market, safeSearch	The country and language Bing answers in, and how strictly it filters adult images.

Output

Every row is labelled with a resultType. Real results for a photo of the Eiffel Tower (long addresses shortened):

[
    {
        "resultType": "image_summary",
        "status": "ok",
        "bestGuess": "Eiffel Tower",
        "suggestedQuery": "Eiffel Tower",
        "bestRepresentativeQuery": "the eiffel tower ________ paris; france",
        "hasText": false,
        "inputWidth": 2900,
        "inputHeight": 4830,
        "inputFormat": "jpeg",
        "similarImagesAvailable": 497,
        "similarImagesReturned": 50,
        "pagesReturned": 50,
        "relatedSearchesReturned": 49,
        "market": "us",
        "searchImage": "https://upload.wikimedia.org/wikipedia/commons/8/85/Tour_Eiffel_Wikimedia_Commons_%28cropped%29.jpg",
        "scrapedAt": "2026-11-08T19:04:20Z"
    },
    {
        "resultType": "similar_image",
        "position": 1,
        "title": "Eiffel Tower 5th Grade Quiz | Quizizz",
        "link": "https://quizizz.com/admin/quiz/.../eiffel-tower",
        "source": "quizizz.com",
        "original": "https://media.quizizz.com/_mdserver/main/media/resource/.../...-v2",
        "originalWidth": 800,
        "originalHeight": 1332,
        "thumbnail": "https://tse3.mm.bing.net/th/id/OIP.etoF3uybCDUssav9b7-ZHQHaMV?r=0&pid=Api",
        "cachedImage": "https://th.bing.com/th/id/R.7ada05deec9b08352cb1abfd6fbf991d?...",
        "fileSize": 179272,
        "format": "jpeg",
        "datePublished": "2025-06-14T03:37:00.0000000Z",
        "dateDiscovered": "2025-06-14T00:00:00.0000000Z",
        "pagesIncludingCount": 171,
        "availableSizesCount": 62,
        "accentColor": "244167",
        "imageId": "2C92A4688465FA063AF14E1D4DAC449BE89F56B9"
    },
    {
        "resultType": "matching_page",
        "position": 1,
        "title": "Torre Eiffel | Torre eiffel, Monumento, Parigi",
        "link": "https://www.pinterest.com/pin/52565520644350730/",
        "source": "pinterest.com",
        "original": "https://i.pinimg.com/736x/47/53/3c/47533c148d0318f8f821cd82d68082cb.jpg",
        "originalWidth": 736,
        "originalHeight": 1308,
        "fileSize": 112350,
        "format": "jpeg",
        "datePublished": "2024-12-30T11:50:00.0000000Z"
    },
    {
        "resultType": "related_search",
        "position": 1,
        "text": "Eiffel Tower Restaurant Paris France",
        "category": "related",
        "searchUrl": "https://www.bing.com/images/search?q=Eiffel+Tower+Restaurant+Paris+France&FORM=IDINTS"
    }
]

(Each row above also carries the fields listed in the table; a few are omitted here for length.)

Other Actors you might need

Actor	What it adds
Yandex Reverse Image Search	The same kind of search on Yandex: pages that carry the picture, similar images, other sizes and text in the picture.
Bing Images Scraper	Start from a keyword instead of a picture: thousands of Bing images per search, with filters.

Frequently asked questions

Is it legal to run a reverse image search on Bing?

The Actor collects publicly available search results, the same ones anyone sees in a browser, and respects the source's limits. Image URLs point to content owned by other people, so check the license and your local rules (including GDPR and CCPA where personal data is visible in a picture) before reusing anything. This is not legal advice.

Do I need a Bing or Microsoft account or an API key?

No. Bing Reverse Image Search works from a picture alone — no Bing or Microsoft account, no Azure key and no API subscription.

Which pictures can I search with?

JPG, PNG, WebP, GIF (the first frame), BMP and TIFF, up to about 25 MB. Give a direct image link, upload a file, or pass a data: link. AVIF and HEIC are not supported; convert them first. A link to a web page rather than a picture is reported as a notice and never fails the run.

Does it identify people in photos?

The Actor has no face recognition of its own. It returns what Bing returns for the picture — its best guess, similar images, the pages that carry it — and what Bing says about people in a photo is up to Bing.

How many similar images can I get for one picture?

It depends on the picture, and on Bing: a rarely published photo may have a few dozen; a well-known landmark or product can have several hundred. Bing is not consistent between runs — one test photo returned about 110 similar images in one run and more than 600 in another, because Bing recognised it slightly differently each time. Set Max results per type to 0 to take everything Bing returns. The number Bing estimates is reported as similarImagesAvailable; it is an estimate and moves between runs.

Why do two runs on the same picture give slightly different results?

Bing orders and trims its lists a little differently from one request to the next, and its best guess can change by a word. The Actor removes duplicates within a picture, but it cannot make Bing repeatable.

Does it download the images?

No. It returns image URLs, Bing's cached copies, thumbnails, sizes and source pages. Download the files you need from those URLs.

Does the market change the results?

Yes. The market sets the language Bing writes in and noticeably changes which pages, related searches and how many similar images it holds for a picture. Run the same picture in two markets to compare.

Can I use Bing Reverse Image Search in Make, Zapier, n8n or my own code?

Yes. Use Apify's integrations, webhooks, the API or the client libraries for JavaScript and Python.

What happens if a run is interrupted?

The Actor saves its progress and picks up where it left off, without repeating or re-charging rows it has already delivered.

Why did I get fewer results than I asked for, or a notice instead?

Situation	What you see	What to do
Bing holds fewer matches for this picture	A shorter list; similarImagesAvailable shows Bing's estimate	Try another market, or a larger version of the picture
The link is a web page, a missing file, or not a picture	One notice row with resultType: "guidance" and a status such as not_an_image (not charged)	Use the direct image address, or upload the file
The picture is too small or too large	A notice with too_small or too_large (not charged)	Use a picture between about 16 pixels and 25 megapixels
Only extras are selected (no similar images, no pages)	A summary row with a hint, plus the extras you chose — no matches	Select Visually similar images and/or Pages containing this image
Bing returned nothing for the picture	A summary row with status: "no_matches" (not charged); any related searches read for its best guess are delivered free	Try a sharper, larger version
Bing declined the picture	A notice with rejected (not charged)	Try another version; if every picture is declined, run again later
Bing did not answer	A notice with bing_unavailable (not charged); the picture is kept for a resume	Run it again later
The run reached its time limit	A final time_limit notice	Raise the run timeout, or search fewer pictures per run
Your maximum cost per run was reached	The run stops after the last row it charged for	Raise the maximum cost per run

Support

• 🌐 Website: flowextractapi.com
• 📧 Email: flowextractapi@outlook.com
• 💬 GitHub: FlowExtractAPI
• 💼 LinkedIn: flowextract-api
• 🐦 X (Twitter): @FlowExtractAPI
• 📱 Facebook: flowextractapi
• 🎵 TikTok: @flowextractapi

Legal & compliance

• Public data only — processes publicly available data.
• Rate limiting — respects source-service limits and terms of use.
• Data protection — no storage of personal information or unauthorized data collection.
• Commercial use — suitable for business intelligence and research.
• No affiliation with or endorsement by Microsoft or Bing is implied.

---

Bing Reverse Image Search — by FlowExtract API. Turn any website into structured data.