Web Search Research x402 offerings

Fetch a URL server-side and extract clean article text as Markdown (Readability-based, like a reader-mode API).

URL extract with a question: ask any web page a question and get structured data as JSON that matches your schema

Web search API for agents: search the web and get result titles, URLs and snippets as JSON

Extract normalized main text and optional links from a public HTTP or HTTPS document. Returns title, author, publication time, language, content hash, truncation and cache state. Output size and fetch time are bounded; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Set include_links=true only when normalized links are needed. Keep fresh=false to reuse cache.

Report declared and heuristically detected document language. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reu…

Extract title, description, author, dates and canonical metadata. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to…

Resolve requested, final and declared canonical URLs with evidence. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false …

Return allowlisted response headers only. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse cache; set fresh=…

Return bounded llms.txt text when publicly available. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse cache…

Convert readable HTML content to bounded Markdown. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse cache; s…

Split readable text into deterministic bounded RAG chunks. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse …

Discover bounded OpenAPI candidate links declared by the requested page. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=f…

Return bounded normalized readable text. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse cache; set fresh=t…

Discover up to five sitemap links declared by the requested page. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to…

Classify MIME type, charset and bounded content length. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse cac…

Extract bounded JSON-LD blocks without executing scripts. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse c…

Extract bounded Open Graph and Twitter Card fields. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse cache; …

Compare the normalized content hash with the previous stored snapshot. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=fal…

Inspect a public HTTP or HTTPS URL and return a structured site passport. Includes pulse fields, registrable domain, robots and sitemap discovery, feeds, OpenAPI hints, and page metadata. Uses at mos…

Return the bounded heading hierarchy from h1 through h6. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse ca…

List up to 100 image references without downloading images. Only public HTTP(S) targets are accepted; JavaScript is not executed. Pass url as an absolute public HTTP(S) URL. Keep fresh=false to reuse…

Use when an agent must read a document as clean Markdown: web page, PDF, DOCX or Korean HWP/HWPX, tables kept. Input: url (http/https) via GET, or POST a file (multipart 'file', raw body, or JSON contentBase64+filename). Free-plan size cap → 413 before payment: HWP 48 KB, HWPX 100 KB XML. Output: JSON markdown, title, pages, sourceType, warnings. Price by detected type: HTML $0.0027, PDF/DOCX $0.0045, HWP/HWPX $0.009. Example: ?url=https://example.com/

Use when an agent needs to know what a URL is before reading it, or to build a link preview or citation. Input: url (public http/https). Output: JSON with final URL after redirects, HTTP status, content type, title, description, site name, language, canonical, preview image, favicon, Open Graph and Twitter tags, RSS/Atom feeds, hreflang alternates, JSON-LD types, robots, first H1. No JavaScript is run. Example: ?url=https://developer.mozilla.org/en-US/

Use when an agent must read a document as clean Markdown: web page, PDF, DOCX or Korean HWP/HWPX, tables kept. Input: url (http/https) via GET, or POST a file (multipart 'file', raw body, or JSON contentBase64+filename). Free-plan size cap → 413 before payment: HWP 48 KB, HWPX 100 KB XML. Output: JSON markdown, title, pages, sourceType, warnings. Price by detected type: HTML $0.0027, PDF/DOCX $0.0045, HWP/HWPX $0.009. Example: ?url=https://example.com/