Scrape
Fetch a URL and get markdown back, with JavaScript executed first.
Fetch a URL and get markdown back, with JavaScript executed first. That last part is the whole point: most of the web renders client-side now, so an HTTP GET returns an empty shell and a markdown converter run over it returns nothing useful.
The output is written for a model to read — headings, links and lists preserved, navigation and chrome dropped — which is what you want when the next step is a summary or an extraction rather than a diff.
If you already know the shape you want out, use extract instead: it takes a schema and returns matching JSON directly, saving you a second call to parse the markdown you just paid for.
Call it
The first response is 402 with the exact price and every rail you can
pay with. Pay, repeat the request with the proof, and you get the result.
curl -X POST https://api.glianalabs.com/v1/tools/scrape \
-H 'content-type: application/json' \
-d '{"url":"https://example.com"}'When to use it
Fetch a web page as clean markdown, JavaScript included. Use when an agent needs the content of a page rather than a search snippet, or when the page renders client-side and a plain fetch returns nothing. Input: url (required, http(s)). Returns url and markdown. Long pages are truncated and the response says so.
What it costs
$0.0050 per successful call — flat, with no plan, minimum or monthly fee. A call that fails validation is refused before it runs, so it is never charged.
Not sure this is the right endpoint? GET /v1/consult?intent=… is
free and answers that.
Often used with this
Card
$0.0200Render a social card in a chosen aspect ratio.
Extract
$0.0100Renders the page (JS included) and returns JSON matching the schema YOU declare, so there is no guessing at field names.
Screenshot
$0.0050Capture a rendered web page as a PNG. Use when an agent needs to show a page rather than read it — a preview, a visual diff, evidence of what a site displayed.