Frequently Asked Questions

An Content Detector is a tool designed to analyze text and determine whether it was written by a human or generated by an AI model (like GPT-5.3, Gemini 3, Claude 5, or Llama 4). It looks for specific linguistic patterns, such as lack of variation in sentence structure ("burstiness") and predictability ("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.

We achieve ~99.9% accuracy on standard essay and article texts. Our multi-model approach minimizes false positives better than any single-model detector. However, no AI detector is 100% perfect, so we recommend using the result as an indicator rather than absolute proof.

We specialize in detecting text from OpenAI models (GPT-5.3, GPT-6), Anthropic (Claude 5 Sonnet, Claude 4.6 Opus), Google (Gemini 3), and Meta (Llama 4).

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.

For free users, we suggest checking texts in chunks of up to 1,500 words for the best speed and accuracy. There is no daily limit on the number of checks you can perform.