Clean Web Pages to Markdown
● Livegrindfree.net
Read a web page as clean Markdown for AI. Use when your agent fetches a URL it did not write: hidden text, comments, invisible Unicode and prompt injections are removed (see removed_count) plus a verdict. Public benchmark: removed 129/129 injections, 0/23 false positives, 72% on an untuned hold-out; Jina Reader 26%, html2text 11%. Honours robots.txt; only successful reads charged. Search intents: url to markdown.
- Price
- $0.002
- Asked in its payment challenge
- Chain
- Base
- Paid in
- USDC
- Live
- 5 of 5 checks
Endpoints
$0.002 asked in its payment challenge on 18 Nov 2026
curl -i -X POST 'https://saferead.grindfree.net/v1/read' \
-H 'Content-Type: application/json' \
-d '{"url":"https://example.com/","mode":"strip","format":"markdown"}'3 more endpoints · on x402 Bazaar
Checks and payment terms on this page refer to the first endpoint's example. Other endpoints have not been checked individually.
Base URLhttps:
- POST/fetch$0.001Fetch a web page URL as clean Markdown for AI, $0.001. Use when your agent just needs a page's readable text: LLM-ready Markdown without scripts, styles, nav or footers, plus title and fetch metadata. Honours robots.txt; only successful reads are charged. No injection stripping: for untrusted pages use /v1/read, which removes hidden text and prompt injections. Search intents: url to markdown, fetch web page.
Example
curl -i -X POST 'https://saferead.grindfree.net/v1/fetch' \ -H 'Content-Type: application/json' \ -d '{"url":"https://example.com/"}' - GET/read$0.002Read a web page as clean Markdown for AI (read clean). Use when your agent fetches a URL it did not write: returns LLM-ready Markdown with hidden HTML, comments, invisible Unicode and prompt injections removed or flagged, plus title, allow|warn|block verdict and fetch metadata. Honours robots.txt. Only successful reads are charged. Search intents: url to markdown, web page to markdown, read url. GET ?url=<page URL> works too.
4 parameters and an example
- urlquery, requiredhttps://example.com/http(s) URL to fetch (ports 80/443; private/internal hosts blocked)
- modequerystrip (default) or flag
- formatquerymarkdown (default) or text
- max_charsqueryMax characters of content returned (default 50000)
curl -i 'https://saferead.grindfree.net/v1/read?url=https%3A%2F%2Fexample.com%2F'
- POST/read-batch$0.004Read up to 10 web pages as clean Markdown in one call (batch read clean), $0.002 per URL. Use when your agent needs several URLs at once: each page returns LLM-ready Markdown with hidden text and prompt injections removed plus a verdict. Honours robots.txt. Only successful reads are charged: if any URL fails, nothing is charged. Search intents: batch url to markdown, read multiple urls.
Example
curl -i -X POST 'https://saferead.grindfree.net/v1/read-batch' \ -H 'Content-Type: application/json' \ -d '{"urls":["https://example.com/","https://example.org/"],"format":"markdown"}'
A dash means the listing gives no price or method. {Braces} mark a value you fill in. Copy buttons copy an example URL.
Agents can find it through the Superstables MCP server and JSON API: GET /api/v1/services/saferead.grindfree.net
Recent checks
- Median response
- 408 ms
- Last checked
- 18 Nov, 09:25 UTC
Our probes look for a payment challenge. They don't test payment or delivery.
All 5 checks
| When (UTC) | Result | HTTP | Response |
|---|---|---|---|
| 18 Nov, 09:25 UTC | Live | 402 | 192ms |
| 16 Nov, 21:23 UTC | Live | 402 | 590ms |
| 15 Nov, 09:22 UTC | Live | 402 | 500ms |
| 13 Nov, 21:24 UTC | Live | 402 | 408ms |
| 12 Nov, 06:26 UTC | Live | 402 | 280ms |
Questions
Did our last probe detect a payment challenge?
At our last probe on 18 Nov, 09:25 UTC, it returned HTTP 402 or another detected payment-challenge signal.
What payment terms does SafeRead advertise?
The listing advertises x402, Base and USDC. It names cdp as its facilitator. Check the seller's current payment challenge and authentication requirements before paying.
Something wrong on this page? Tell us.