# 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; assess returns a 3-model verdict in ~5–10 seconds; verify runs the full eight-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 evaluate source quality, logical structure, and claim precision. 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. 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

Lenz is a fact-checking API for AI-generated content. The full verify pipeline has five stages:

1. **Framing** — The submitted text is cleaned and neutralised into an atomic, verifiable statement. The system identifies the topic domain, key entities, and generates targeted search queries.

2. **Research** — The system searches the web for relevant evidence, scoring each source for authority.

3. **Debate** — We use two separate AI models to argue opposing sides. One argues the claim is true, the other argues it is false. Each side then delivers a rebuttal, stress-testing the other's reasoning.

4. **Panel Review** — Three separate AI models evaluate the debate and evidence: a Source Reliability Auditor, a Logic & Reasoning Examiner, and a Precision & Accuracy Analyst. Each provides an independent score and explanation.

5. **Conclusion** — The scores are aggregated into a final verdict: True, Mostly True, Mixed, Mostly False, or False, along with a Lenz Score from 1 (completely false) to 10 (completely true) and an executive summary.

## Research

- [Beyond Benchmarks: Disagreement Among Frontier LLMs on Real-World Fact-Checks](https://lenz.io/research/llm-disagreement): 5 frontier LLMs vs ~1000 real user 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
- [Plans & Pricing](https://lenz.io/plans): Self-serve plans from Free to Scale — per-tier /verify, /assess, and /ask quotas, monthly and annual billing
- [LLM Hallucination Detection](https://lenz.io/hallucination-detection): Detect hallucinations in model output — extract claims, verify each against real sources
- [Verify AI Output](https://lenz.io/verify-ai-output): Fact-check AI-generated documents and content claim by claim
- [Automated Fact-Checking](https://lenz.io/automated-fact-checking): Fact-checking in the publishing pipeline — auto-approve or flag for human review
- [Fact-Checking Tool for Editors & Reviewers](https://lenz.io/fact-checking-tool): Browser Workbench for hands-on review plus the API for automation
- [MCP Server](https://lenz.io/integrations/mcp-server): Remote Model Context Protocol server at lenz.io/mcp. Connect Lenz to Claude Desktop, Claude Code, Cursor, or any MCP client with a Bearer API key. Exposes fact-checking tools: assess (fast 3-model verdict), verify (full pipeline), get_verification (poll), ask (grounded follow-up on a completed verification), select (resolve ambiguity), and check_usage (quota). Streamable HTTP transport.
- [Integrations](https://lenz.io/integrations): Hub for every way to connect Lenz — the n8n node (live), Zapier (coming soon), the MCP server, the CLI, and the REST API. One API key across all of them.
- [n8n Integration](https://lenz.io/integrations/n8n): The Lenz node, published on n8n.io — add a fact-check step to any n8n workflow. Returns structured JSON: verdict (True/Mostly True/Mixed/Mostly False/False), lenz_score (1–10), a citations array (url, title, stance), and the reasoning trace. No HTTP configuration; the API key goes under Credentials → Lenz API.
- [API Quickstart](https://lenz.io/docs/quickstart): Five-minute integration guide — get an API key, make the first call, and read a verification result, with Python and TypeScript examples
- [Error Reference](https://lenz.io/docs/errors): Canonical reference for every SDK exception and API error code
- [Public API Documentation](https://lenz.io/api/v1/docs/): Read-only REST API for third-party developers. Endpoints include: search and browse published claim verifications, retrieve full claim verifications with framing, research sources, debate transcripts, adjudication assessments, and conclusions. Also lists available domains/entities for filtering. No authentication required.
- [OpenAPI Specification](https://lenz.io/api/v1/openapi.json): Machine-readable OpenAPI 3.0 schema for the public API

## Policies

- [Terms of Use](https://lenz.io/terms): Terms and conditions for using Lenz
- [API Terms](https://lenz.io/api-terms): Terms for API and developer-platform use
- [Privacy Policy](https://lenz.io/privacy): How we collect, use, and protect personal information
- [Contact](https://lenz.io/contact): Get in touch with the Lenz team

**Terms of Use** — Users must be 13+ to use the service. Lenz uses AI to automate verification analysis and does not guarantee accuracy. Claims added to the Library are publicly visible. Subscriptions are billed monthly via Stripe and can be cancelled at any time.

**Privacy Policy** — Lenz collects account information (email, name) and claim submission data. Claims added to the Library are public. Data is not sold to third parties. Cookies are used for authentication and analytics. Users can request data deletion by contacting the team.