See what your AI is actually claiming. Verify the claims that matter.

POST /extract Free · 1000/day

# AI-generated brief in — atomic claims out
brief = """
Albert Einstein won the 1921 Nobel Prize
in Physics for his theory of general
relativity. He developed the special
theory of relativity in 1905 while
working as a patent clerk in Bern.
Born in Ulm in 1879, he emigrated to
the US in 1933 and joined the Institute
for Advanced Study.
"""

out = client.extract(text=brief)
for c in out.identified_claims:
    print("-", c)
# - Albert Einstein won the 1921 Nobel
#   Prize in Physics for his theory of
#   general relativity.
# - Albert Einstein developed the special
#   theory of relativity in 1905 while
#   working as a patent clerk in Bern.
# - Albert Einstein emigrated to the
#   United States in 1933.

Drop into CI tomorrow as “report what factual claims our AI made yesterday.” Zero spend, real signal.

POST /verify ~90s · 7-model panel

# verify the one that looks confident
v = client.verify_and_wait(
    claim=out.identified_claims[0],
).verdict

print(v.label, v.score, v.confidence)
# → "false" 1.0 0.97
# 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

A research desk of seven models works the claim. Returns a report with citations, not a similarity score.

Python 3.9+

# pip install lenz-io
from lenz_io import Lenz

client = Lenz(api_key="lenz_...")
v = client.verify_and_wait(
    claim="Einstein won the 1921 Nobel Prize "
          "for general relativity.",
)
print(v.verdict.label, v.verdict.score)
# false 1.0

TypeScript Node 18+

// npm install lenz-io
import { Lenz } from "lenz-io";

const client = new Lenz({ apiKey: "lenz_..." });
const v = await client.verifyAndWait({
  claim: "Einstein won the 1921 Nobel "
       + "Prize for general relativity.",
});
console.log(v.verdict?.label, v.verdict?.score);
// false 1.0