# Visual Product Search API: Identify Products from a Photo (`tenfoldfleet/visual-product-search`) Actor

Identify a product from a photo: paste product image URLs and get the recognised product name, category, the shop and web pages that show the same picture, similar images, related shopping searches and text read from the image. $5 per 1,000 images; images without a result are free.

- **URL**: https://apify.com/tenfoldfleet/visual-product-search.md
- **Developed by:** [Tenfold Fleet](https://apify.com/tenfoldfleet) (community)
- **Categories:** E-commerce, Agents, MCP servers
- **Features:** Limited permissions
- **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $2.50 / 1,000 image identifieds

This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events.
Since this Actor supports Apify Store discounts, the price gets lower the higher subscription plan you have.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

An Actor is a serverless cloud program that runs on the Apify platform. It has two run modes.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.

Apify vocabulary and the platform model are defined once, in the agent quickstart at https://apify.com/agents.md.

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For examples already wired to this Actor's own input schema, see the [API](#api) section below.

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).

# README

### What does Visual Product Search do?

**Visual Product Search** takes the URL of a product photo and tells you **what the product is and where it is sold or shown online**. For each image you get the recognised **product name**, its **category**, the **web pages and retailers that carry the same picture**, **visually similar images**, **related shopping searches** and any **text printed on the product**.

Use it as a **visual product search API**: send a list of image URLs and get one row per image in JSON, CSV or Excel. Run it from the Apify Console, the [Apify API](https://docs.apify.com/api/v2), a schedule, or an AI agent through the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp).

Results come from the public Bing Visual Search pages, read without a login. Not affiliated with Microsoft, Bing or Google. This Actor does not use Google Lens and returns no Google data.

### Why use it?

- **Name an unknown product.** Resellers and thrift sellers can turn a photo of an item into a product name to list or price it.
- **Find who else sells it.** Ecommerce sellers see which stores and marketplaces show the same product picture.
- **Build price comparison and catalogue tools.** Match a supplier photo to a known product name and to the pages that carry it, then fetch prices from those pages.
- **Check a supplier.** See whether a "factory" photo is a stock picture used by dozens of other shops.
- **Enrich listings.** Add a category, a short description and related search phrases to products that arrive with only a photo.

### What data can it extract?

![Sample output of Visual Product Search API: Identify Products from a Photo, rows from a real run: Image, Product, Category, Pages, Sites, Related searches](https://api.apify.com/v2/key-value-stores/4TBgG7fopkYMNWnX2/records/visual-product-search-output.png)

| Field | What it holds |
|---|---|
| `inputImage` | The image you sent |
| `productName` | The product the engine recognised, for example "Nike Free 4.0 Flyknit Bright Crimson" |
| `bestSearchQuery` | The most common search phrase for this image, when the engine gives one |
| `category`, `categoryPath` | Product type, for example "athletic shoes or sneakers", and its full path |
| `description` | A short generated description of the product, when the engine gives one |
| `pagesFound` | How many pages carry the image |
| `retailerDomains` | Unique domains of those pages |
| `retailerPages[]` | `title`, `url`, `domain`, `thumbnail` of each page that carries the image |
| `similarImages[]` | `imageUrl`, `pageUrl`, `title` of visually similar pictures |
| `relatedSearches[]` | Related search phrases, shopping phrases first |
| `textLines[]` | Text read from the image (brand, model, label) |
| `offers[]` | `seller`, `price`, `currency`, `url`, `title`. A bonus field, not a guarantee: see below |
| `searchedAt` | Time of the search (UTC) |

**How often each field is filled.** In our bench of 40 product photos on the Apify platform (10 Nov 2026, up to 5 tries per image; the Actor now makes up to 8), 37 came back with a result and 3 were not recognised (free). Of those 37: 36 had a product name, 27 had at least one page that carries the image, all 37 had similar images, 33 a description, 16 text read from the image, 12 a category, 12 related searches and 0 price offers.

### How to identify a product from a photo

1. Copy the **direct link to the product image** (right-click the picture, then "Copy image address"). A link to the web page around it is not an image link.
2. Paste one or more links into **Product image URLs**.
3. Optional: choose a **Market** such as `en-GB` or `de-DE`, and set how many retailer pages and similar images to keep.
4. Click **Start**. An image takes about 5 to 20 seconds; 12 run at the same time.
5. Open the **Products** view, or download the dataset as JSON, CSV or Excel.

### How much does it cost?

You pay **$5 per 1,000 images identified** ($0.005 per image), however many pages and similar images come back. An image counts only when it returns a product name or at least one page that carries it. These are **free** and come back as a row with an `error` field:

- images the engine does not recognise after 8 tries (`noResult`),
- broken or unreachable image links (`unreachable`, `invalidUrl`),
- results with no product name and no pages (`empty`),
- lookups stopped by a bot check or a network failure (`challenge`, `failed`).

There is also an Actor start fee of $0.00005 per run. **Apify free plan:** a run searches the first 3 images of your list; any paid plan removes the limit. Set a **maximum cost per run** and the Actor stops when it is reached. If the platform moves a long run to another server, images that already have a row are not searched or charged again.

### Input

```json
{
    "imageUrls": [
        "https://images.unsplash.com/photo-1542291026-7eec264c27ff?w=800",
        "https://images.unsplash.com/photo-1505740420928-5e560c06d30e?w=800"
    ],
    "market": "en-US",
    "maxPages": 50,
    "maxSimilarImages": 20,
    "includeOcr": true
}
```

### Output

One row per image. Download it as JSON, CSV or Excel, or read it through the API.

```json
{
    "inputImage": "https://images.unsplash.com/photo-1542291026-7eec264c27ff?w=800",
    "productName": "Nike Free 4.0 Flyknit Bright Crimson",
    "bestSearchQuery": null,
    "category": "athletic shoes or sneakers",
    "categoryPath": ["human made object", "fashion cosmetics or accessories", "shoes", "athletic shoes or sneakers"],
    "description": "This product image showcases the Nike Free 4.0 Flyknit \"Bright Crimson\" running shoe, featuring a breathable knit upper, white Nike swoosh, and a translucent sole.",
    "pagesFound": 63,
    "retailerDomains": ["shoebrands.org", "wallpapercave.com"],
    "retailerPages": [
        {
            "title": "The #1 Best-Selling Shoe Brand of All Time (2026) - Shoe Brands",
            "url": "https://www.shoebrands.org/what-shoe-brand-has-been-sold-the-most-all-time/",
            "domain": "shoebrands.org",
            "thumbnail": "https://tse2.mm.bing.net/th/id/OIP.UJE-cBCmQ-5aJMvYagMZMwHaE8?r=0&pid=Api"
        }
    ],
    "offers": [],
    "similarImages": [
        {
            "imageUrl": "https://wallpapercave.com/wp/wp10013668.jpg",
            "pageUrl": "https://wallpapercave.com/running-shoes-wallpapers",
            "title": "Running Shoes Wallpapers - Wallpaper Cave"
        }
    ],
    "relatedSearches": [],
    "textLines": ["J", "NIKE"],
    "errorType": null,
    "error": null,
    "searchedAt": "2026-11-10T02:41:07.000Z"
}
```

A failed image looks like this and is not charged:

```json
{
    "inputImage": "https://example.com/logo.png",
    "errorType": "noResult",
    "error": "The engine did not recognise this image after 8 tries. It works best with a clear photo of one product; logos, drawings, screenshots and images its fetcher cannot download usually fail. Not charged.",
    "searchedAt": "2026-11-10T02:41:19.000Z"
}
```

### Tips

- **Use clear product photos.** One product, plain background, at least 400 pixels wide. Lifestyle shots with several objects give vaguer names.
- **Stock photos get a generic name.** A picture of unbranded headphones comes back as "Black Over-Ear Wireless Headphones"; a picture of a branded item usually comes back with brand and model.
- **The name is the engine's best guess.** Check `retailerPages` and `textLines` before you rely on a brand or model for pricing.
- **Pages are pages that show the picture, not only shops.** Blogs, news sites and wallpaper sites appear next to retailers. Filter `retailerDomains` to the stores you care about.
- **Brand-new store photos often have a name and no pages.** A picture that only one shop uses may not be indexed on other pages yet.
- **Change the market** to see local retailers and local related searches.

### FAQ

#### Is this Google Lens?

No. It reads a different visual search engine and returns no Google Lens results. If you need a product name, a category and the pages that carry a product photo, it covers the same job at a fixed price per image.

#### Does it return prices?

Sometimes, and you should not count on it. `offers` is filled only when the engine attaches seller prices to an image result. In our bench of 40 product photos it was empty for every image. Treat it as a bonus field; to get prices, fetch the pages in `retailerPages`.

#### How is this different from Reverse Image Search?

[Reverse Image Search](https://apify.com/tenfoldfleet/reverse-image-search) answers "which sites use this exact photo?" with a different engine and returns only pages. Visual Product Search answers "what product is this and who sells it?": it adds the product name, category, similar products, related shopping searches and text read from the image.

#### Can I upload a file instead of a URL?

Not yet. The image must be reachable at a public URL. Upload the file to any public host or to an Apify key-value store and use that link.

#### Why did an image fail?

The engine opens a result only for images it recognises. Logos, drawings, screenshots, very small pictures and images on hosts that block its fetcher usually fail. Each image is tried up to 8 times on fresh connections before it is reported as `noResult`, and failed images are free.

#### How many images can I send in one run?

Up to 5,000, and the same URL listed twice is searched once. 12 images are searched at the same time; our 40-image bench took 77 seconds, so 1,000 images take roughly 30 to 40 minutes. The default run timeout is 4 hours. A run that reaches its timeout or your maximum cost stops cleanly, and its status message says how many images were left.

### Disclaimer

This Actor reads publicly available search result pages only. It does not log in and does not collect private data. Product names, categories and descriptions are produced by the search engine and can be wrong; verify them before using them in listings or pricing. Product photos and trademarks belong to their owners. You are responsible for using the results in line with the law and with the terms of the sites involved.

### More tools from Tenfold Fleet

| Actor | Output |
|---|---|
| [1688 Product Details API: Price Tiers, MOQ, Specs & Supplier](https://apify.com/tenfoldfleet/1688-product-details-scraper) | product details |
| [1688 Products Search: Wholesale Prices, Sales & Suppliers](https://apify.com/tenfoldfleet/1688-products-search) | product |
| [Alibaba Scraper - Wholesale Suppliers, MOQ & Price Breaks](https://apify.com/tenfoldfleet/alibaba-products-scraper) | product |
| [Amazon Product Scraper - Details, Prices & Search by ASIN](https://apify.com/tenfoldfleet/amazon-product-scraper) | product |
| [Coles Product Scraper - Australian Supermarket Prices & Deals](https://apify.com/tenfoldfleet/coles-product-scraper) | product |
| [JD Products Scraper - JD.com Keyword Search with Prices](https://apify.com/tenfoldfleet/jd-products-scraper-keyword-search-prices) | product |
| [Shopify Products Scraper - Inventory, SKUs, Variants & Stock](https://apify.com/tenfoldfleet/shopify-products-scraper) | product |
| [Walmart Product Details - Price, Stock & Seller by Item ID](https://apify.com/tenfoldfleet/walmart-product-details) | product |
| [Woolworths Product Scraper - AU Shelf Prices, Specials & GTINs](https://apify.com/tenfoldfleet/woolworths-product-scraper) | product |
| [1688 Alibaba AliExpress Image Search: Compare Prices by Photo](https://apify.com/tenfoldfleet/1688-alibaba-aliexpress-image-search) | matched product |
| [1688 Image Search API - Reverse Image Search for Factory Prices](https://apify.com/tenfoldfleet/1688-image-search-suppliers-by-photo) | image search |
| [ALDI Australia Scraper - AU Products, Unit Prices & Catalogue](https://apify.com/tenfoldfleet/aldi-australia-scraper) | product |

All 122 tools: [apify.com/tenfoldfleet](https://apify.com/tenfoldfleet). If this Actor saves you time, save it (the bookmark on its Store page) and leave a review: both help other people find it. Found a bug or need another field? Tell us on the Issues tab of this page.

# Changelog

This Actor's version history is a separate document: https://apify.com/tenfoldfleet/visual-product-search/changelog.md

# Actor input Schema

## `imageUrls` (type: `array`):

Direct links to public product photos (JPG, PNG or WebP), not web pages. One image = one result row. Clear photos of a single product work best; logos, drawings and screenshots are often not recognised and come back as a free error row. Up to 5,000 images per run. On the Apify free plan a run searches the first 3 images; any paid plan removes the limit.

## `market` (type: `string`):

Language and country the search runs in, as language-COUNTRY: en-US, en-GB, de-DE, fr-FR, es-ES, it-IT, ja-JP and so on. It changes which retailers and related searches come first.

## `maxPages` (type: `integer`):

Keep at most this many pages that carry the image (retailerPages). pagesFound always shows how many were found. The price per image is the same either way.

## `maxSimilarImages` (type: `integer`):

Keep at most this many visually similar images (the engine returns up to 35). 0 leaves them out.

## `includeOcr` (type: `boolean`):

Return the text printed on the product or its packaging (brand, model, label) in textLines when the engine can read any.

## Actor input object example

```json
{
  "imageUrls": [
    "https://images.unsplash.com/photo-1542291026-7eec264c27ff?w=800",
    "https://images.unsplash.com/photo-1505740420928-5e560c06d30e?w=800"
  ],
  "market": "en-US",
  "maxPages": 50,
  "maxSimilarImages": 20,
  "includeOcr": true
}
```

# Actor output Schema

## `results` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "imageUrls": [
        "https://images.unsplash.com/photo-1542291026-7eec264c27ff?w=800",
        "https://images.unsplash.com/photo-1505740420928-5e560c06d30e?w=800"
    ]
};

// Run the Actor and wait for it to finish
const run = await client.actor("tenfoldfleet/visual-product-search").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "imageUrls": [
        "https://images.unsplash.com/photo-1542291026-7eec264c27ff?w=800",
        "https://images.unsplash.com/photo-1505740420928-5e560c06d30e?w=800",
    ] }

# Run the Actor and wait for it to finish
run = client.actor("tenfoldfleet/visual-product-search").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "imageUrls": [
    "https://images.unsplash.com/photo-1542291026-7eec264c27ff?w=800",
    "https://images.unsplash.com/photo-1505740420928-5e560c06d30e?w=800"
  ]
}' |
apify call tenfoldfleet/visual-product-search --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,tenfoldfleet/visual-product-search"
        }
    }
}
```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/4L1brARsrVhFautOh/builds/y5FhnHByAbTzBQeh1/openapi.json
