Skip to main content
Help Center

Frequently Asked Questions

Everything you need to know about our detection technology, accuracy, and privacy policies.

General Overview

An AI detector is a tool that analyses text and estimates how likely it is to have been generated by a large language model such as ChatGPT, Claude, Gemini or Llama, rather than written by a person. It looks for linguistic patterns typical of machine output: low variation in sentence structure ("burstiness") and highly predictable word choice ("perplexity").
Yes, our core detection features are completely free for individual users. You can scan unlimited text without needing to create an account or provide credit card details.
Our tool is built for everyone:
  • Educators checking student assignments.
  • Writers wanting to prove the authenticity of their drafts.
  • SEO Professionals ensuring content won't be penalized by search engines.
  • Editors verifying freelance submissions.

How it Works

No AI detector is reliable enough to be treated as proof. Published testing puts the better detectors in the 80–95% range on clearly AI or clearly human samples, and accuracy falls sharply on text that has been edited, translated, paraphrased or written in a heavily formulaic style. Treat the score as one signal alongside draft history and a conversation with the author — never as the sole basis for an academic or employment decision.
It is built to recognise output from current general-purpose models: OpenAI's ChatGPT and GPT-4o/GPT-5, Anthropic's Claude, Google's Gemini and Meta's Llama. Because it scores statistical writing patterns rather than matching a fixed list of models, it also flags output from models it has not seen before.

Privacy & Safety

Absolutely not. Your privacy is paramount. Text is processed in RAM (temporary memory) during the analysis and is permanently discarded once the result is shown. We do not use your text to retrain our models or share it with third parties.

Account & Limits

Each scan accepts between 50 and 50,000 characters — roughly 8,000 words. There is no daily limit on the number of scans. Very short samples are the bigger problem in practice: under about 150 words there is not enough signal for a stable score.

Still have questions?

Can't find the answer you're looking for? Our friendly team is here to help.

Contact Support