Web Search Research x402 offerings

Start an async deep research task and poll the returned run ID for results.

Extract relevant content from one or more URLs.

Parallel web search with structured results and excerpts.

Search podcasts. Searches the podcast catalog by show name — the canonical podcast search.

Search podcast episode content. To find podcasts (shows) by name or topic, use /v1/podcasts/search?q=….

List and search podcasts. Returns a paginated list of podcasts, with filters for topic, language, suitability tier, popularity, and format.

Search Paul Graham's source corpus — a source-grounded persona of the Y Combinator co-founder and essayist, built from 13,000+ cited sources: his complete essays, talks, interviews, and X posts — by …

Search Paul Graham's source corpus — a source-grounded persona of the Y Combinator co-founder and essayist, built from 13,000+ cited sources: his complete essays, talks, interviews, and X posts — by semantic + lexical query and retrieve grounded packets (graded claims, quotes, evidence with citations). POST a JSON body { query, limit? (<=100), packetTypes? }. Flat micro-price per query.

Use when an agent needs a web page as clean text for RAG, LLM prompts or indexing: fetched server-side, boilerplate/ads/nav stripped, returned as title + headings + paragraphs + plain text. Batch mode: repeat urls= up to 5 times. Also asked as: page to text, url to markdown, scrape a page, web page to clean text.

Coverage timeline for a topic from the GDELT Project: pick metric volume (share of all monitored coverage — is a topic heating up or cooling down) or tone (average-tone trend). Returns normalized time-series points plus the latest value and a rising/falling/flat trend. One upstream call.

Runet search bundle: up to 10 queries in one payment, 10% off (Пакет поиска по рунету: до 10 запросов одним платежом, скидка 10%)

Research pack: Cyrillic search + top pages as Markdown (Research-пакет: кириллический поиск и top-страницы в Markdown)

Runet search bundle: up to 100 queries in one payment, 20% off (Пакет поиска по рунету: до 100 запросов одним платежом, скидка 20%)

Russian web page converted to LLM-ready Markdown (RU-страница в LLM-ready Markdown)

Deep research pack: 3 searches + up to 10 pages as Markdown (Research-пакет deep: 3 поиска и до 10 страниц в Markdown)

English Wikipedia fact lookup: search by query or exact title, returns intro extract as plain text. For agents that need a grounded summary before deeper web search. Not a substitute for primary sources.

Metadata and structure of a PDF (URL): pages, page size, title, author, creator, dates, version, encryption, form fields, attachments, bookmarks (table of contents) and whether it has extractable text or is a scan.

PDF to text: extract the text of any public PDF, page by page. The text of a public PDF, page by page: pass ?url= of a whitepaper, filing, invoice or paper and get every page's text with page markers, the page count and the file size. Parsed with pdf.js; up to 15 MB and 200 pages. A file that is not a PDF, will not open, or has no text layer (scanned images) is refused before any charge.

Fetch a PDF from a URL and extract its text content. Returns page count, document info, and the full text (up to 20MB PDFs).

Check robots.txt before crawling or scraping a page. Decide whether GPTBot, ClaudeBot, Googlebot, or another crawler may fetch the exact URL and return ALLOW/DENY, winning rule, crawl-delay, sitemap URLs, and live provenance.

Real-time web search for AI agents. Search the web for current and up-to-date information, news, facts, research, documentation, and sources beyond model training data. Returns ranked structured JSON results with title, URL, description, and position for web grounding, RAG retrieval, research, and fact-finding. Send query, optional limit, and optional freshness as URL parameters. Keyless x402 pay-per-call; no API key, account, or subscription required.

Extract webpage metadata for agent research and URL triage: title, description, canonical URL, Open Graph, and Twitter metadata from a public page.

Get PennyAPI-observed Texas HHSC regulatory changes for a childcare business: before/after values, detection time, and authoritative source context. Search by facility name; no government identifier required.

Refresh a domain's public RDAP registration state and return PennyAPI-observed before/after changes for registrar, expiration, RDAP last-changed, EPP statuses, and nameservers. Use the free /v1/domain/observe first to establish a baseline.