Your agent deserves
better data.

Pay-per-parse · USDC on Base · Built for Agents

Scraping APIs were built for developers. NanoParse is built for agents — pay per parse, no subscriptions, $0.01 flat. Every parse returns clean Markdown plus Litmus — machine-readable signals on freshness, authority, and citability.

Try it free Quick Start
$0.01
Per parse
x402
Agent-Native
10
Free parses
Litmus
Agent Intel
How it works

URL in. Rich data out.

Your agent sends a URL. We render it in a real browser, run content scoring to isolate the article, compute Litmus — 15 machine-readable signals on freshness, authority, and citability — and return clean Markdown with author, dates, language, and structured data.

01

Agent sends a URL

Your agent calls POST /fetch with any web URL. First 10 parses free per network (subnet), lifetime — one bucket shared across your whole network. No account, no API key, no human required.

02

402 — Payment Required

The API returns x402 payment terms. Your agent's wallet signs a $0.01 USDC micropayment automatically.

03

Browser renders the page

Headless Chromium on the edge. NanoParse fully executes JavaScript, waits for the network to idle, and reliably renders complex SPAs before converting the DOM to Markdown.

04

Litmus scores the content

Smart block-level scoring strips navigation, footers, ads, and cookie banners — keeping the article intact. Litmus then runs 15 deterministic signals — source authority, freshness, hedge-language density, syndication, paywall detection — so your agent knows whether to trust and cite the page. No LLM call, zero extra cost.

05

Metadata extracted

OpenGraph, Twitter Cards, schema.org JSON-LD, favicon, language, word count — everything scraped from the raw HTML and attached to the response.

06

Markdown delivered

Clean, structured Markdown returned with full metadata payload. Ready for your agent to consume, store, or analyze.

Visual proof

Raw HTML noise → Pristine Markdown intelligence

NanoParse renders full JavaScript, strips every piece of boilerplate, and preserves complex data tables — so your agent sees exactly what it needs, nothing less, nothing more.

✗ BEFORE — RAW DOM JUNK
<html>
  <head>
    <script>!function(f,b,e,v,n,t,s){if(f.fbq)return;n=f.fbq=function()
    {n.callMethod?n.callMethod.apply(n,arguments):n.queue.push(arguments)};if(
    !f._fbq)f._fbq=n;n.push=n;n.loaded=!0;n.version='2.0';n.queue=[];t=b.creat
    eElement(e);t.async=!0;t.src=v;s=b.getElementsByTagName(e)[0];s.parentNode.
    insertBefore(t,s)}(window,document,'script','https://connect.facebook.net/en
    _US/fbevents.js');</script>
    <link rel="stylesheet" href="/bundle.7f8a3c.css">
  </head>
  <body class="template-article">
    <div class="top-banner-ad">
      <iframe src="https://ad.doubleclick.net/..."></iframe>
    </div>
    <nav id="sticky-header">
      <ul><li><a href="/">Home</a></li>
      <li><a href="/sports">Sports</a></li>
      <li><a href="/opinion">Opinion</a></li></ul>
    </nav>
    <aside class="sidebar">
      <div class="trending-widget">Most Read</div>
      <div class="newsletter-cta">Sign up for our newsletter</div>
    </aside>
    <div id="content">
      <div class="article-header">
        <h1>Study Finds Correlation Between Diet and Longevity</h1>
      </div>
      <p>A comprehensive 20-year study published in <em>The Lancet</em> has found
      a strong correlation between dietary patterns and increased lifespan.</p>
      <table class="data-table">
        <thead><tr><th>Diet</th><th>Avg Lifespan</th><th>Sample</th></tr></thead>
        <tbody><tr><td>Mediterranean</td><td>83.4 yr</td><td>n=12,400</td></tr>
        <tr><td>Standard Western</td><td>76.1 yr</td><td>n=11,800</td></tr></tbody>
      </table>
      <div class="in-article-ad">
        <img src="/ad-300x250.jpg" alt="Sponsored">
      </div>
    </div>
    <footer>
      <div class="cookie-banner">We use cookies to improve your experience.</div>
      <div class="related-articles">You may also like...</div>
      <div class="comments-section">42 Comments</div>
    </footer>
  </body>
</html>
✔ AFTER — CLEAN MARKDOWN + TABLES
# Study Finds Correlation Between Diet and Longevity

*By Jane Chen, Health Correspondent*

A comprehensive 20-year study published in *The Lancet* has found
a strong correlation between dietary patterns and increased lifespan.

| Diet              | Avg Lifespan | Sample    |
| ----------------- | ------------ | --------- |
| Mediterranean     | 83.4 yr      | n=12,400  |
| Standard Western  | 76.1 yr      | n=11,800  |

Researchers noted that participants following a Mediterranean diet showed
a 7.3-year increase in average life expectancy compared to the control group.

The study controlled for socioeconomic factors and exercise habits across
24,200 participants in seven countries.
+ LITMUS — WHAT YOUR AGENT NOW KNOWS
{
  "source": { "type": "news", "authority": 0.72 },
  "freshness": { "published": "2026-01-14", "age": "7 months ago" },
  "tldr": "20-year study links Mediterranean diet to a 7.3-year increase in average lifespan.",
  "structural_trust_score": { "level": "high", "trust_factors": ["Moderate-authority source"] },
  "content_type": "news_article"
}
Try It

Parse a page. Free.

Try it instantly — no signup, no wallet. 3 free tries per day right here on this page — separate from your 10 free parses via the /fetch API or MCP server. No account required. After that, $0.01 per parse via x402.

Rate-limited — 3 free tries per IP, per day.

FAQ

Questions agents would ask.

Straight answers for developers wiring up NanoParse.

Does this work on React, Vue, and heavy JavaScript sites?
Yes. Standard scrapers fail on modern SPAs because they only fetch raw HTML. NanoParse spins up a headless Chromium instance at the edge, fully executes all JavaScript, and waits for dynamic content to load before running content isolation algorithms.
Does my agent need a wallet?
For x402 payments, yes — the agent signs each payment from a self-custodied wallet holding USDC on Base. If your agent doesn't have one, run npx @coinbase/payments-mcp: the agent gets a Coinbase wallet, funds it via Apple Pay, and pays for services automatically. Docs → Self-custody via Coinbase — no seed phrases, and nothing runs through NanoParse. Every network (subnet) still gets 10 free parses before any payment is needed.
What is x402?
An open payment protocol backed by Coinbase and Cloudflare. Uses HTTP 402 — reserved since 1992 — to let machines pay each other. Agent gets a 402 with payment terms, signs a USDC transaction, retries.
What is Litmus?
Structured intelligence about every page — source authority, freshness, structural trust score, hedge-language density, content density, content type, syndication status, key figures, reading time, and a TL;DR. Computed at the edge, no LLM call, zero extra cost. Learn more →
How is this different from Firecrawl?
Firecrawl sells to humans: accounts, plans ($16–$599/mo), API keys. NanoParse is agent-native: no account, no plan. Agent discovers endpoint, pays per-call, moves on. See full comparison →
Works with Claude Code / Cursor?
Yes. MCP server at nanoparse.app/mcp. Add to config, agent auto-discovers the tool. Quick Start →
What about gas fees?
Gas fees are $0.00001. Your total cost is $0.01 per parse. Your wallet signs an off-chain EIP-3009 authorization (the x402 protocol); the payment provider absorbs the gas. You pay one number: $0.01.
What happens if a parse fails or the page can't render?
You're never charged for a parse that doesn't succeed. Blocked, invalid, or abusive URLs are rejected before any charge — those never cost anything. And settlement only happens after a page renders successfully, so a failed render is simply never charged at all. Recently parsed URLs return instantly from cache, and retrying with the same signed payment is free.
From the Blog

Agent-native engineering.
Straight from the source.

Deep dives into agent-native infrastructure, the x402 payment protocol, MCP tool design, and what it takes to make the web accessible to AI agents — written by the team building it.

Read the Blog →