Catch AI hallucinations before they ship.

LLM hallucination detection, done the honest way: Lenz pulls every verifiable claim out of your model's output, researches each against real independent sources, and returns a sourced verdict with citations — not a confidence guess from another model grading its own kind.

Wire it into CI to catch regressions, or gate answers at runtime before they reach a user.

What a detected hallucination looks like.

A real model-written claim, verified by the real pipeline. Click through for the full evidence.

Built for RAG hallucinations, too.

Groundedness checkers tell you whether an answer is faithful to your retrieved context — not whether that context is actually right. Lenz works the other way: it extracts the claims from your model's answer and verifies each against fresh independent sources, catching what those tools miss — an answer built faithfully on a retrieved document that is itself wrong or out of date.

How detection works.

Three API primitives chain into a detection pipeline:

• POST /extract pulls the verifiable claims out of any model output (free, 1000/day).
• POST /assess returns a fast 3-model panel verdict per claim in ~5-10s.
• POST /verify runs the full 8-model pipeline with citations on the claims that matter (~90s).

Evidence-grounded, not self-grading: verdicts come from research across real sources, argued through an adversarial debate and scored by independent reviewers — with the full audit trail attached.

Why multi-model beats a single checker.

A model grading its own vendor's output isn't independent — and a single checker inherits a single model's blind spots. Lenz runs frontier models from rival vendors against each other: one argues the claim is true, one argues it's false, and three independent reviewers adjudicate on the evidence.

The disagreement is the signal. When the panel splits, you see it — individual scores, not a blended guess.

Detect hallucinations in 10 lines

# model output in — hallucinations out
from lenz_io import Lenz

client = Lenz(api_key="lenz_...")
claims = client.extract(text=model_output).identified_claims
r = client.assess(text=" ".join(claims))

for c in r.claims:
    if c.verdict == "False":
        print("HALLUCINATION:", c.claim, c.confidence)
# HALLUCINATION: Albert Einstein won the 1921 Nobel Prize ... high

Not an inline guardrail. An investigator.

Millisecond guardrails classify against the model's own context — fast, cheap, and blind to anything outside it. Lenz sits at the other end of the latency-fidelity axis: it researches each claim against fresh, independent sources and shows its work. Use a guardrail to filter; use Lenz when you need to actually know — and to prove it.

See our open evaluation of where frontier models disagree on real-world fact-checks →

Pricing

Start free, no card required. /extract is free at 1,000 calls/day.

Compare all plans on the plans page →

Frequently asked questions

By use case

Catch the next hallucination before a customer does.

Self-serve from day one. Free tier, no card required.