# Lenz

> Fact-checking API for AI-generated content — an independent verification layer that returns sourced verdicts with citations and a full reasoning trace.

Lenz verifies AI-generated content before it is published, returned to a customer, or passed to another agent. It is API-first: four primitives — extract, assess, verify, ask — with Python and TypeScript SDKs. extract pulls checkable claims out of AI output, or out of a public web page given its URL; assess returns a 3-model verdict in ~15 seconds; verify runs the full multi-model pipeline (Framing → Research → Debate → Panel Review → Conclusion) in ~90 seconds; ask answers grounded follow-up questions about a completed verification. Research grounds each claim in external sources scored for authority, and three independent reviewers on models from different vendors each check source quality, how directly the evidence bears on the claim, and claim precision; when enough quotes have been checked against their pages, one of them reads only those. Every verdict is structured — a conclusion label (True, Mostly True, Mixed, Mostly False, or False), a Lenz Score from 1 to 10, citations, and the reasoning trace — so workflows can block, publish, or escalate automatically. When no public record in the evidence settles a claim, the answer is "No Public Record" with no score (lenz_score is null), which does not make the claim false. Lenz is unaffiliated with any model vendor, and API-submitted claims are private.

## How It Works

- [About Lenz](https://lenz.io/about): The company — what Lenz is and who it fact-checks AI output for
- [How It Works](https://lenz.io/how-it-works): Five-step verification pipeline from claim framing to conclusion

## Research

- [Beyond Benchmarks: Disagreement Among Frontier LLMs on Real-World Fact-Checks](https://lenz.io/research/llm-disagreement): 5 frontier LLMs vs 997 user-submitted claims. Full methodology, breakdowns, and the per-claim CSV at https://lenz.io/research/llm-disagreement/data.csv. Permanent citation: https://doi.org/10.5281/zenodo.20344846 (resolves to the current version). Every version and every study: https://lenz.io/research

## Developer

- [Developers](https://lenz.io/developers): Fact-checking API for AI- and human-written documents — four primitives (/extract, /assess, /verify, /ask) with Python and TypeScript SDKs; /extract also reads a public web page given its URL
- [Plans & Pricing](https://lenz.io/plans): Self-serve plans from Free to Scale — per-tier /verify, /assess, and /ask quotas, monthly and annual billing
- [Warranty](https://lenz.io/warranty): What Lenz warrants, and when it pays
- [Product: fact-checking for AI-drafted text](https://lenz.io/product): What Lenz checks and where it runs — inside Claude or Cursor, from a script, or through the API — with one page per audience
- [For content teams](https://lenz.io/for/content-teams): Fact-check articles, briefs and posts before they go out — a result and the sources per statement
- [For tax and legal teams](https://lenz.io/for/tax-and-legal): Fact-check an AI-drafted tax or legal memo — forms, deadlines, thresholds, what a court held; a result per statement, and a check that the cases, statutes and EU acts it cites say what the sentence claims, for US and EU law, UK legislation and German federal law. Not a citator
- [For AI product teams](https://lenz.io/for/ai-product-teams): Hallucination detection against public sources — each factual statement in a model answer checked, with structured results
- [For marketing teams](https://lenz.io/for/marketing-teams): Fact-check the claims in marketing copy against public sources — market figures, competitor prices, comparative claims
- [MCP Server](https://lenz.io/integrations/mcp-server): Connect Lenz to Claude Code, Codex, Cursor, or any MCP client — fact-checking tools (assess, verify) over Streamable HTTP with your API key
- [Integrations](https://lenz.io/integrations): Every way to connect Lenz — Claude and ChatGPT, the n8n node, the Zapier app, the MCP server, the CLI, and the REST API
- [Lenz in Claude or ChatGPT](https://lenz.io/integrations/claude-chatgpt): Connect Lenz to Claude or ChatGPT and ask the chat to check a claim — a verdict, a score from 1 to 10 (or "No Public Record" when no public record settles the claim, which does not make it false), and citations come back in the thread. No API key for either: Claude connects in one click, ChatGPT as a custom app you add by its address (beta)
- [n8n Integration](https://lenz.io/integrations/n8n): The Lenz node on n8n.io — add a fact-check step to any workflow, no HTTP configuration, returns verdict, score, and citations as structured JSON
- [Zapier Integration](https://lenz.io/integrations/zapier): The Lenz app for Zapier — add a fact-check step to any Zap, one trigger and six actions, returns verdict, score, and sources as mapped fields
- [API Quickstart](https://lenz.io/docs/quickstart): Five-minute integration guide — first API call to verified verdict
- [Going to Production](https://lenz.io/docs/production): Webhooks, polling, stopping a run, timeouts and retries, per-call options and batch
- [Public API Documentation](https://lenz.io/api/v1/docs/): Read-only REST API for searching claims and retrieving full verification reports
- [OpenAPI Specification](https://lenz.io/api/v1/openapi.json): Machine-readable OpenAPI 3.0 schema for the public API

## Policies

- [Terms of Service](https://lenz.io/terms): The terms for the API, the connector, the website and WhatsApp
- [Privacy Policy](https://lenz.io/privacy): How we collect, use, and protect personal information
- [Subprocessors](https://lenz.io/subprocessors): The third parties that receive the text you submit
- [Contact](https://lenz.io/contact): Get in touch with the Lenz team