Integrate TinEye’s reverse image search engine to automatically search and retrieve results from the TinEye index.
Search TinEye using our API.
The TinEye API allows you to automate searching for images against TinEye's ever-growing multibillion index of web images. Use TinEye's image recognition to find out where an image came from, how it is being used or if modified versions of the image exist.
Your developers can integrate our TinEye API using our REST/JSON interface. Or you can simply use our API browser extensions to search manually, as often as you like.
Powering billions of searches
Ideal for image moderation and verification
Fast search through billions of images
Active web indexing with a large and growing cross-section of the images on the web
Find heavily cropped and modified versions of images
Ideal for brand monitoring and copyright compliance
How it works
The TinEye API is a fully hosted API. There is no software to install and no updates to worry about. By using our hosted API, you save time and money needed to build and maintain your own image recognition solutions.
Easy to integrate
The TinEye API is easily integrated with your existing technology, regardless of the languages and tools you use.
The TinEye API is a REST-based API, delivered over HTTP or HTTPS in JSON format. REST/JSON bindings are available in all major programming languages. We also support a growing number of language-specific libraries to make integration very straight forward. Our documentation and libraries are extensive.
Scalable and high performance
Multiple image query support including JPEG, PNG, or GIF. Query images can be specified by a publicly accessible image URL, or uploaded.
Large and growing image index
The TinEye API searches the TinEye index which is an index of a large cross section of the web. The TinEye index is at 18 billion images today.
Built by TinEye's image recognition scientists and backed by a decade of research and development, the TinEye API is the ideal reverse image search solution for image search and verification.
Frequently asked questions
Q.How can I get started with the TinEye API?
- Create an account using our signup form.
- You will receive access to a special user interface.
- You will also receive a unique API key which provides access to the API.
- Purchase a pre-paid search bundle and start searching!
Q.Does my search bundle expire?
Search bundles expire after two years. Unused searches may not be carried forward.
Q.How do I use the API?
There are two ways to use the API to search TinEye:
- Easy: a special graphical user interface on the TinEye Commercial API site, very similar to the one at tineye.com. This interface is accessible once you are logged in to your API account. Simply click on the “Search” tab.
- Advanced: integrate the API with your own system directly. Please see our documentation for more information.
Q.Can I have multiple users on one account?
Q.Can the API find images that aren't on the web?
No. The TinEye Commercial API can only show you matches that exist within TinEye’s index.
If you need reverse image search for your own image collection or image database, take a look at our MatchEngine API.
Q.Is there a non-commercial API?
Not at the moment.
Q.What are the terms of service?
Q.Where can I find technical documentation for the API?
Please see our documentation for complete technical documentation.
Q.How do I buy API searches?
- Log in to your API account, or sign up if you do not have an API account.
- Once you are logged in, click the “Buy Searches” tab and follow the instructions.
Q.How do I see how many searches I have left?
- Log in to your API account;
- Click the Account tab.
- The “Account Summary” page shows key information about your search bundle(s), including the expiry date, how many searches have been done, and how many searches remain.
Q.How should I format my search images?
Images should be in the JPEG, PNG, GIF, BMP, or TIFF format with a maximum file size of 1 megabyte. TinEye works best with images that are at LEAST 300 pixels in either dimension, but can work with images as low as 100 pixels in either dimension. For best results, avoid visibly watermarked images as TinEye may search for the watermark and not the image itself.