Paste any text and find out whether it was written by a human or generated by an AI (ChatGPT, Claude, Gemini, etc.). Free — 5 checks per day with a Google account.
AI language models like ChatGPT, Claude, and Gemini produce text with characteristic patterns: unusually consistent sentence length, high-frequency "filler" transitions ("Moreover", "It is worth noting"), and a tendency to avoid concrete personal anecdotes. This detector analyzes those patterns using a language model trained to distinguish machine prose from human writing.
For best results, submit at least 150–200 words. Heavily edited or paraphrased AI text will score lower on the AI probability meter, because the human editing obscures the original model's stylistic fingerprint.
It sends your text to a large language model that analyzes writing patterns, sentence structure, vocabulary distribution, and stylistic markers that differ between human and AI-generated prose.
No detector is 100% reliable. Results are a probabilistic signal. Heavily edited AI text, paraphrasing, or very short passages may produce inaccurate results on any detector.
Login lets us enforce fair-use limits (5 checks per day) so the tool stays free. We store only your Google ID, email, and name — we never read or post anything on your behalf.
The detector is model-agnostic. It flags text from ChatGPT (GPT-4, GPT-4o), Claude, Gemini, Llama, Mistral, Cohere, and other large language models.
No. We only log metadata (character count, result label, probability). The text you paste is never saved to our servers.