Paste a text that may have come from Perplexity and see which sentences read like output from an AI chat. The demo below checks a section of up to 3,000 characters without signing in; with a free account you see all seven detectors side by side.
Six more detectors
Perplexity is a search engine that answers using a language model. It uses its own Sonar models and, on paid plans, models from other makers too, so there is no single “Perplexity style”.
The answer is also based on the sources it finds, and it summarises them. Detectors measure even sentences and predictable word choice in it, as with other models. But a person may have written the source, so read the result as a starting point and not as proof.
Which model wrote the text. The result does not say that the text came from Perplexity specifically. The differences between models are smaller than the differences caused by the prompt or by later edits, and an independent detector has no key to their watermarks.
Nor can it reliably recognise text that someone thoroughly rewrote, translated or mixed with their own after generating it. With text like that the detectors disagree and the result is borderline.
An answer from Perplexity contains link numbers and a list of sources. The full check automatically leaves out the reference list and quotations with a source, but the demo without signing in evaluates the whole pasted section, so delete them first.
Sentences taken word for word may shift the result in either direction. So check the marked sentences against the linked source before drawing any conclusions.
A high score is not proof that the text came from Perplexity, and a low one is not proof of the opposite. No AI text detector is one hundred per cent accurate.
When you check someone else's text, take the result as a basis for questions: why the author chose this source, what the term in the second paragraph means, how they reached the conclusion. When you check your own, it shows you the passages worth rewriting in your own words.
No. Perplexity adds the links itself and a link does not say who wrote the sentence. Check whether the source really says what the text claims.
You cannot tell that from the text. Perplexity uses its own models and models from other makers, and the check does not determine which of them answered.
At least 100 characters; a continuous paragraph or a whole chapter is more reliable. With just a few sentences the result is indicative only.
Yes. The check measures the properties of machine writing in general, not the signature of a particular model, so you can check text from ChatGPT and other models in the same way.
Texts up to 300,000 characters, seven detectors at once, colour-marked sentences and a history of your checks. The account is free and needs no card.