Free ChatGPT detector to check any text
A free ChatGPT detector for any text. Paste it, upload a file, or drop in a link.
Check your textHow to read your AI detector score
The AI detector gives you a single number from 0 to 100. It is the estimated chance that AI wrote the text, not a yes or no. Here is what each band means.
Probably a person
Reads like human writing. We did not pick up the patterns a model tends to leave behind.
Hard to say
Some of it leans one way, some the other. Read it yourself before you draw a conclusion.
Probably AI
This has the marks of machine-written text. Read it closely before you conclude anything.
How the ChatGPT detector works
Three steps, a few seconds, no setup.
Add your text
Paste it, upload a Word or PDF file, or drop in a link to the page you want to check.
We check the patterns
The model weighs your text against the way ChatGPT writes and the way people write.
Read the score
You get a number from 0 to 100 and a plain read on how likely AI was involved.
What gives ChatGPT away
ChatGPT writes in a way that is fluent but oddly even. Sentences tend toward a similar length. The next word is usually the safe, expected one. It hedges, it repeats sentence shapes, and it explains more than the moment calls for.
People write with more friction. A blunt short line. A tangent. A word that is not quite the obvious choice. Our ChatGPT detector is trained on heaps of ChatGPT writing sitting next to human writing, so it learns those differences instead of reading for meaning the way you do.
How accurate is this ChatGPT detector?
On clean test text the model is right most of the time, comfortably above nine in ten. Real writing is messier, so read the score as a strong hint, not a fact. Nobody can promise certainty here, and you should be wary of anyone who does.
Two things lower the odds. Very short text, because there is not enough to go on. And edited text, because once a person rewrites a ChatGPT draft or runs it through a paraphraser, the tells fade. A low score means nothing jumped out, not that ChatGPT was never involved.
From GPT-4 to GPT-5.5
The detector reads output from across ChatGPT's history, from the GPT-3.5 and GPT-4 era through GPT-4o, GPT-4.1, the GPT-5 generation released in mid-2025, and the GPT-5.5 family that arrived in 2026. Older models leave heavier tells and are easier to flag. The newest models write with more variety, which makes any detector's job harder, so treat borderline scores on very recent text with extra care.
- Nov 2022 ChatGPT launches on GPT-3.5
- Mar 2023 GPT-4
- May 2024 GPT-4o
- Apr 2025 GPT-4.1
- Aug 2025 GPT-5
- Apr 2026 GPT-5.5
- May 2026 GPT-5.5 Instant (default for ChatGPT)
Where your text goes
The check happens in memory on our own server. As soon as you have a score, your text is dropped. No logs, no database, no training set.
There is no account holding a history of your checks either.
ChatGPT detector FAQ
Is the ChatGPT detector free?
Yes. The whole tool is free, with no account and no cap on how many checks you run.
Does it work on GPT-5 and GPT-5.5?
Yes. It reads output across ChatGPT's generations. Newer models are harder to flag, so weigh borderline scores carefully.
Can teachers use it on student work?
You can, but use it as a prompt to look closer, never as proof on its own. No detector is reliable enough to accuse someone.
Will it catch ChatGPT text I edited?
Sometimes. Light edits often slip through. Heavy rewriting or paraphrasing can hide the tells well enough to fool it.
Can I upload a file or a link?
Yes. Upload a Word or PDF file, or paste a web address, and we'll pull the text out for you.
Does it work on Claude or Gemini too?
Yes. The same model covers Claude, Gemini and others. For general use, try the main AI detector.