TokenCounter.cc is designed to be private by default. This policy explains, in plain language, what happens to your data when you use the site.
The token counter runs entirely in your web browser using client-side JavaScript. The text you paste, type or upload is processed locally on your own device. It is never transmitted to our servers, never logged, and never stored. There is no backend that receives your content. When you close or refresh the tab, the text is gone.
If you use the "Upload file" option, the file is read locally in your browser to count its tokens. It is not uploaded to any server.
To keep the page lightweight, the GPT tokenizer library is loaded on demand from a public content-delivery network (esm.sh). Your typed text is not sent to that CDN — only the tokenizer code is downloaded to your browser. The CDN may, like any web server, record standard request metadata (such as your IP address and user agent) when the library file is fetched.
We may use privacy-respecting, aggregate analytics to understand overall traffic (for example, page views and country-level data). Any such analytics do not capture the text you enter into the tool.
The core tool does not require cookies to function. If advertising (such as Google AdSense) or third-party services are added in future, those providers may use cookies to serve and measure ads. You can control cookies through your browser settings, and where required we will provide a consent mechanism. This section will be updated if and when such services are introduced.
This site is a general-audience developer tool and is not directed at children under 13.
We may update this policy as the site evolves. Material changes will be reflected by the "last updated" date above.
Questions about privacy? Visit our contact page.