FREE AI Hallucination Detector · no signup

Is your AI making things up?

Paste any AI-generated answer and we'll check it claim by claim — flagging fabricated facts, unsupported statements and invented citations before they reach your readers.

Works with ChatGPT Claude Gemini Perplexity & any LLM
AI Hallucination Detector
Claim-by-claim fact verification · with sources
0 / 3 free checks today
0 / 500 words
Or try a sample:
RESULT
IDLE

No text checked yet

Paste an AI answer or try a sample. We'll score its reliability and flag every shaky claim.

WHAT WE CATCH

The four ways AI lies to you

Large language models are fluent, not factual. We separate what's grounded from what's guessed.

Fabricated facts

Confident statements that are simply untrue — wrong dates, fake statistics, invented events presented as established fact.

Invented citations

Plausible-looking sources, papers, authors and URLs that don't exist — the single most common academic AI failure.

Unsupported claims

Assertions with no verifiable backing — opinions stated as facts, extrapolations, and over-confident generalizations.

Internal contradictions

Claims that conflict with other statements in the same answer — a tell-tale sign the model is improvising.

Source verification PRO

Every supportable claim is matched to real web sources you can click through and verify yourself.

PRO

Exportable report PRO

Download a full reliability report — every claim, verdict and source — to share with editors, teachers or clients.

PRO
HOW IT WORKS

From answer to audit in seconds

1

Paste the AI text

Drop in any LLM answer — a paragraph or a full essay. Nothing is stored.

2

We break it into claims

Each factual statement is isolated and checked against what's verifiable.

3

Read the verdict

A reliability score plus a color-coded breakdown — and sources on Pro.

FAQ

Common questions

What is an AI hallucination?
A hallucination is when an AI model states something false or unverifiable with total confidence — a made-up statistic, a fake citation, a wrong date, or an event that never happened. Because the text reads fluently, these errors are easy to miss. This tool surfaces them so you can fix or remove them before publishing.
How does the checker decide what's a hallucination?
We split the text into individual claims, then assess each one for verifiability, internal consistency, and the linguistic patterns that correlate with fabrication (false precision, hedging, invented specifics). On Pro, each supportable claim is additionally matched against live web sources.
Is it 100% accurate?
No automated checker is perfect — treat the result as a prioritized list of what to double-check, not a final ruling. It dramatically narrows where to focus your fact-checking, especially on long answers, but a human should confirm anything high-stakes.
Which AI models does it work with?
Any of them. Paste output from ChatGPT, Claude, Gemini, Perplexity, Llama, or any other LLM — the analysis is on the text itself, so the source model doesn't matter.
Do you store the text I paste?
No. Free checks are analyzed transiently and never used for training. Pro checks can be saved to your private history if you choose, and deleted any time.
Limited offer TEXTSIGHT YEARLY Get every tool for 25% less. Switch to a yearly plan and save 25% across all 20 TextSight tools — Pro, Business & every detector. One subscription, everything included. Claim 25% off Billed yearly · cancel anytime

Don't publish what the AI invented.

Fact-check any AI answer in seconds — free, no signup, nothing stored.

Check an answer