80trust / 100

Markdown Clean

by NetIntel in AI models & inference

x402 APIPassing, checked just now

Convert messy HTML or text into clean, well-structured Markdown using Claude Haiku — strips boilerplate, fixes heading hierarchy, normalizes lists and links, and returns readable Markdown so agents can feed clean docs into downstream pipelines, knowledge bases, or LLM context.

POST https://netintel.dev/markdown/clean

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
255 ms typical, 324 ms slowest 5%
Last check
just now
Next check
in 26 min

How to call it

# See the payment challenge (nothing is charged)
curl -i -X POST "https://netintel.dev/markdown/clean" \
  -H "content-type: application/json" \
  -d '{"text":"<nav>Home About</nav><h1>Welcome</h1><p>Hello <a href=\"https://example.com\">world</a>.</p><footer>© 2024</footer>"}'
import { wrapFetchWithPayment } from "@x402/fetch";
import { x402Client } from "@x402/core/client";
import { ExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

const client = new x402Client().register(
  "eip155:8453",
  new ExactEvmScheme(privateKeyToAccount(process.env.AGENT_KEY)),
);
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? Preflight it first for $0.005:
// GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fnetintel.dev%2Fmarkdown%2Fclean
const res = await pay("https://netintel.dev/markdown/clean", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({"text":"<nav>Home About</nav><h1>Welcome</h1><p>Hello <a href=\"https://example.com\">world</a>.</p><footer>© 2024</footer>"}),
});
console.log(await res.json());

Example input

{
  "text": "<nav>Home About</nav><h1>Welcome</h1><p>Hello <a href=\"https://example.com\">world</a>.</p><footer>© 2024</footer>"
}

Example output

{
  "cached": false,
  "findings": [],
  "grade": "A",
  "input_chars": 108,
  "markdown": "# Welcome\n\nHello [world](https://example.com).\n",
  "output_chars": 39,
  "reduction_ratio": 0.64,
  "score": 100
}

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
just nowPassed402260 ms$0.03
4 h agoPassed402252 ms$0.03
7 h agoPassed402255 ms$0.03
11 h agoPassed402243 ms$0.03
15 h agoPassed402186 ms$0.03
18 h agoPassed402255 ms$0.03
22 h agoPassed4021.1 s$0.03
26 h agoPassed402299 ms$0.03
29 h agoPassed402324 ms$0.03
34 h agoPassed402178 ms$0.03