Scrape public Telegram channels without login or API key: posts with date, text, views, reactions, links, hashtags, media; channel subscribers and engagement analytics (posts per day, median views, view rate, top hashtags and linked domains). One search per call (result caps in the input schema); failed lookups are not charged.

Scrape Dice US tech jobs by keyword and location with Dice filters (date, contract/full-time, remote, direct hire vs recruiter, visa sponsorship): salary, employer type, description, address, contacts, tech stack. No login. One search per call (result caps in the input schema); failed lookups are not charged.

Scrape StepStone jobs (Germany, Belgium, PNet South Africa) by keyword and location with filters: full ad text, contact email and phone from the ad, salary or StepStone estimate, home office, employment type, industry, agency flag. No login. One search per call (result caps in the input schema); failed lookups are not charged.

Scrape Wellfound (AngelList Talent) startup jobs by role and city or remote: full description, salary and equity ranges, job type, remote policy, experience, plus startup pitch, size, stage and signals (top investors, growing fast). No login. One search per call (result caps in the input schema); failed lookups are not charged.

Daily economic-health read from keyless multi-source data (markets, VIX, Treasury yield curve, FX, World Bank) into a healthScore + risk regime with drivers, tracked day over day - flags regime changes, yield-curve inversion and stress. Signals, not advice. Agent-callable. One search per call (result caps in the input schema); failed lookups are not charged.

Give it drug names (brand or generic). For each it fuses four openFDA sources - approvals, FAERS adverse events (total, top reactions, serious, deaths), recalls and the boxed warning - into ONE composed safety brief. Keyless, agent-callable. FAERS reports do not establish causation. One search per call (result caps in the input schema); failed lookups are not charged.

Crawl a site and get clean markdown for every page, in one call. Same-host BFS with depth and page-budget limits, robots.txt honoured by default. $0.0015 per requested page (1-25).

Capture high-quality screenshots of any webpage using headless browser.

Local business search via Google Places. Returns names, addresses, categories, ratings, reviews, phone numbers, websites, and coordinates.

Extract structured data from any webpage using JSON schema. AI-powered extraction that understands page context.

Fetch webpage with full JavaScript rendering using headless browser. Perfect for SPAs, React/Vue apps, and dynamic content that requires JS execution.

Extract text and metadata from PDF documents. Supports page-specific extraction and returns structured content.

Screens names of people or companies against keyless public sanctions lists - OFAC SDN and the UN Security Council Consolidated List (names + aliases). Returns one brief per name: scored possible matches + a review signal. Signals for human review, NOT a verdict; a name match is not identity proof. Up to 3 items per call; failed lookups are not charged.

Discover a site's URLs without fetching page content. Reads robots.txt sitemap directives, sitemap.xml and nested sitemap indexes, falling back to homepage link extraction.

Cheap bulk page text: fetch 1-20 URLs and get clean markdown, truncated to a per-page cap. $0.0015 per URL.

One call: allow / caution / block for any website, with reasons. Phishing & malware blocklists, domain age, Tranco popularity, TLS, email/DNS, brand impersonation and storefront red flags. Built for AI agents before they pay or click - one synchronous API call. Up to 3 items per call; failed lookups are not charged.

Fetch and convert any webpage to clean markdown. Fast, no JavaScript rendering. Perfect for static content, articles, and documentation.

A company profile from its domain, read live from its own site: what it sells and to whom, pricing and plans, NAICS sector, self-reported head count band, open roles from its Greenhouse/Lever/Ashby board, tech stack, socials, security.txt role contacts, and the domain's registrar, age, email provider, SaaS vendors and SPF/DMARC posture. Each AI-read field names its source page; coverage flags show what was found.

Full transcript of any YouTube video with timestamps. Accepts a video ID or any YouTube URL.

Multi-step research in one call: plans sub-questions, searches each, fetches and dedupes sources, and synthesizes an answer with inline [n] citations, key findings, and gaps. Tiers: quick = 1 search / 5 sources ($0.08); standard = 3 sub-questions / 8 sources ($0.20); deep = 5 sub-questions / 12 sources ($0.35). Default: standard.