The fact-checking API for AI output. Human-written works too.

POST /extract Free · 1,000/day

# AI-generated brief in — atomic, verifiable claims out
brief = """
Looking at the data, Einstein had a remarkable career. He won the
1921 Nobel Prize in Physics for his theory of general relativity,
which most physicists consider one of the most important scientific
achievements of all time. His famous equation E=mc² was first published
in 1905, the same year he completed his PhD at the University of Zurich.
"""

out = client.extract(text=brief)
for c in out.identified_claims:
    print("-", c)
# Opinions and meta-commentary skipped; pronouns resolved; compound sentences split:
# - Albert Einstein won the 1921 Nobel Prize in Physics for his theory of general relativity.
# - Albert Einstein first published the equation E=mc² in 1905.
# - Albert Einstein completed his PhD at the University of Zurich in 1905.

Free, so it can run on every draft before a credit is spent.

text can also be a single public web page URL (http or https, nothing else in the field). Lenz reads the page, or a YouTube video's transcript, and extracts the claims from its first 50,000 characters. Pages behind a login (Facebook, Instagram, Threads, LinkedIn) can't be read. A URL call typically takes 5-40 seconds: SDK 2.13 and later wait up to 90 seconds; with an older SDK, create the client with Lenz(timeout=90) (Python) or new Lenz({ timeoutMs: 90000 }) (Node).

POST /assess ~10s · 3-model panel

# fast verdict from a 3-model frontier panel
r = client.assess(text="Albert Einstein won the 1921 Nobel Prize in Physics for his theory of general relativity.")
for c in r.claims:
    print(c.verdict, c.confidence)
    if c.rationale:
        print(c.rationale)
# False high
# The 1921 prize was awarded for his explanation of the photoelectric effect, not for relativity.

# a list of up to 20 in one call — one row per claim, same order
rows = client.assess(claims=["Water boils at 100 °C at sea level.", "Drinking coffee lowers the risk of heart disease."]).claims
for c in rows:
    print(c.verdict, c.confidence)
    if c.dissent:
        print("One reviewer disagreed:", c.dissent)
# True high
# Mostly True low
# One reviewer disagreed: The studies show an association, not that coffee itself lowers the risk.

# escalate low-confidence claims to /verify
if r.claims[0].confidence == "low":
    deep = client.verify_and_wait(claim=r.claims[0].claim)

One text, or the claims /extract returned in a single call. Mobile pre-flight, or any UI where users wait for an answer. Use confidence to decide when to escalate.

rationale is the reasoning of a reviewer who agrees with the panel's verdict; dissent, when set, is the reasoning of the reviewer farthest from it. Both are reviewers' notes, not checked sources; for sourced evidence, call /verify.

POST /verify ~90s · multi-model pipeline

# deep check with citations
v = client.verify_and_wait(claim="Albert Einstein won the 1921 Nobel Prize in Physics for his theory of general relativity.")

print(v.verdict, v.lenz_score, v.confidence)
# → "False" 1 "high"
# The 1921 Nobel was awarded for the photoelectric effect, not relativity.

for s in v.sources[:2]:
    print(s.title, s.url)
# → "Albert Einstein at UZH" — uzh.ch

Multiple models orchestrated through a purpose-built verification pipeline: framing → research → debate → panel review → conclusion. Returns a report with reasoning and citations.

POST /ask Q&A on a verification

# follow up on any verification
reply = client.ask.send(
    v.verification_id,
    message="What did Einstein actually win the 1921 Nobel Prize for?",
)
print(reply.content)
# → The photoelectric effect, not relativity. The Nobel committee cited his
#   1905 paper on the discovery of the law of the photoelectric effect.

Ground a chat thread on the verification's evidence. Same citations, same model, no re-research per turn.

POST /review 2–4 min · the whole ladder

# a whole draft in; the issues and the suggested rewrites out
draft = "The EU AI Act took effect in March 2024. It sorts AI systems into four risk tiers."

review = client.review_and_wait(text=draft)
for i in review.issues:
    print(i.verdict, i.claim)
    if i.suggested_rewrite:
        print("  Suggested rewrite:", i.suggested_rewrite)
# False The EU AI Act took effect in March 2024.
#   Suggested rewrite: The EU AI Act entered into force on 1 August 2024.

Extract, assess and verify in one call: the claims that come back negative or low-confidence get the full pipeline, up to a cap you set. review_and_wait polls for you; pass webhook_url to be called instead.