Web operations.
Give your code or your agent the live web. A real browser renders the page — JavaScript included — and returns Markdown, structured data, a PDF or a PNG. Every URL fetch is SSRF-guarded and capped — one end of the document-to-web pipeline, on the same key as documents & data.
Operations
7 operations, priced each
Prices are per successful call. 1 unit = $0.002; the free tier covers 500 units a month.
URL → Markdown
Render the live page and return clean, readable Markdown — for RAG, notes and agents.
read_urlScrape
One render → rendered HTML, every link, and page metadata.
scrape_pageURL → PDF
Snapshot the live, rendered page as a pixel-faithful PDF.
url_to_pdfScreenshot
Capture the live page as a PNG — viewport or full scroll height.
url_to_screenshotBatch
Markdown for up to 10 URLs in one call.
batch_scrapeCrawl
The root page plus same-origin pages, all as Markdown.
crawl_siteMap
Discover the same-origin URLs on a page — the site map, no content fetched.
map_siteFull price table · Every parameter, in the interactive reference
Quickstart
From curl
# URL → Markdown ($0.004) curl https://api.preteworks.com/v1/web/markdown \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url":"https://example.com"}' # Full-page screenshot ($0.01) curl https://api.preteworks.com/v1/web/screenshot \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"url":"https://example.com","fullPage":true}' -o shot.png
From an AI agent instead? Add the MCP server — the same operations appear as tools.