374 services carry this tag in their source record. Tags come from the provider, not from us — a tag is a claim about what the service does, not proof that it does it well.
Public HTML URL to bounded Markdown, source URL, retrieval time and content hash. No JavaScript, login, PDF or CAPTCHA bypass. Unsupported or oversized content fails before settlement. Reuse request_key and the original...
Fetch a public web page and return only its metadata: title, description, canonical URL, language, site name, author, publish date, image and JSON-LD.
Web search via Tavily. Returns top N results with URL, title, content snippet, score.
Run a CSS selector against an HTML string and return the matches (text, attrs, and optionally outerHTML for each). The deterministic alternative to regex when you already have the HTML and know the selector - pairs with...
Extract a <table> from an HTML string as JSON rows (header-keyed) or CSV. Useful for prices, schedules, sports stats, or anything an agent has already fetched as HTML. If multiple tables match, the first is used.
Inspect a PDF without downloading the whole thing into your model: page count, title, author, subject, creator, producer, creation/modification dates, encryption flag, and byte size. Body: {"url":"https://…/file.pdf"}.
Every link on a web page with its anchor text, split into internal and external, with nofollow flags and the most-linked external domains. Use for SEO audits, crawling, backlink research or broken-link checks.
Enumerate every <a href> in an HTML string with its anchor text and rel attribute. Optionally resolves relative hrefs against a base URL and filters by a regex on the href. The deterministic way to crawl a page's outlink...
Extract <title>, <meta description>, OpenGraph/Twitter cards, canonical URL, and JSON-LD blocks from an HTML string. Distinct from /api/meta which fetches a URL - feed this the HTML you already have (from /api/render, /a...
Detect whether a public page changed since the last hash, with a compact diff.
Strip all HTML tags and return plain text. Preserves block-level structure (paragraphs and headings become newline-separated). hiddenContent reports text a reader cannot see (HTML comments, display:none or hidden element...
Request an https URL and report whether it is reachable, its status, every redirect hop with timings, key and security headers (HSTS, CSP and others), and the TLS certificate with its issuer, the names it covers and the...
Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; mark...
Expand a shortened or redirecting URL: follows the redirect chain server-side and returns every hop plus the final destination, re-validating each hop against SSRF.
Extract webpage metadata, OpenGraph and JSON-LD for one public URL. Scalar single-URL contract for MCP and autonomous buyer runtimes.
User agent parser. Parse a User-Agent string into browser and version, operating system and version, device type (desktop, mobile, tablet or bot) and, for crawlers, which bot it is: Googlebot, Bingbot, GPTBot, ClaudeBot,...
Check an email or web page for text a person reading it would not see but an AI reading it would: HTML comments, display:none or hidden elements, white-on-white or off-screen text, zero-width and tag characters, base64 t...
Convert a web page to Markdown: fetch a public URL and return clean readable text, optionally with JavaScript or a screenshot. Input: url, format, js. Returns title, Markdown and status. Use when an agent needs the text...
Breached password check: is this password in known data breaches, and how often? Send only the SHA-1 hash (never the password); just the first 5 characters reach Have I Been Pwned (k-anonymity). Up to 50 hashes per call.
Link-preview metadata of a web page: title, description, Open Graph and Twitter card image, site name, author, publish date, language, canonical URL, favicon and RSS feeds. Use to build link previews, enrich bookmarks or...
Detect the technologies a website uses from its headers and HTML: CMS (WordPress, Shopify, Webflow), frameworks (Next.js, React, Vue), CDN and hosting (Cloudflare, Vercel), analytics, chat, payments. Use for lead qualifi...
Fetch URL content as Markdown: read any web page and get clean Markdown - navigation, ads and boilerplate stripped, links resolved, plus a real token count. The same extraction /search uses on result pages, exposed stand...
Web page to markdown: give a public URL, get its main content as clean Markdown for LLMs (navigation, footers and scripts removed) with title, canonical URL, language, publish date and links. Use when an agent needs to r...
OpenAI-compatible chat completion with Qwen3 30B (fast mixture-of-experts model): set the base URL to /v1/llm/qwen3-30b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call,...