Web Search Research x402 offerings

Probe any public URL and report if it is an x402 paywall - price, network, payTo, scheme. Shop paywalls before you spend. Try GET /probe/sample.

Read any public web page and return its main article content as clean Markdown (readability extraction, boilerplate/nav/ads stripped) — no HTML parsing needed on your side. Body: {url: string (http/https, publicly reachable)}.

Summarize text (article, transcript, report) into a given number of sentences, via Claude Haiku 4.5. Preserves the source text's language. JSON body: {text: string (max 8000 chars), max_sentences?: integer 1-10 (default 3)}.

Current top N Hacker News stories (title, url, score, author, comment count) — tech/startup news ranking. Optional parameter: ?limit=<n> (1-50, default 20).

Semantic web search (understands intent, not just keyword matching) — for an agent that needs current information, facts, or sources beyond its training data. Returns ranked results (title/url/content snippet) plus an optional AI-generated direct answer, via Tavily. JSON body: {query: string, num_results?: integer 1-10 (default 5)}.

Structured Google search results (organic listings, direct answer box, related questions) — for an agent that needs to know what Google actually ranks for a query (competitive research, SEO/brand monitoring, fact-checking search visibility). JSON body: {query: string, country?: 2-letter ISO code (default 'us')}.

Wikipedia article summary (extract, short description, thumbnail image, canonical link) for a given title — CC BY-SA content, attribution included in every response. Parameters: ?title=<exact article title> (e.g. Bitcoin), ?lang=<language code> (default en).

GenesisBlock: Global political headlines and policy update summaries.

GenesisBlock: Latest sports scores and breaking news across major leagues.

Get the five newest spaceflight and space-industry news stories with titles, summaries, sources, URLs, images, and publication times. Use this endpoint for current rocket launch, NASA, SpaceX, satellite, mission, or spaceflight news research.

Scrape a public webpage and extract clean readable text. Use this web scraping endpoint when an AI agent needs page content for summarization, research, retrieval, content extraction, indexing, or do…

Get a current U.S. weather forecast from NOAA and the National Weather Service by latitude and longitude. Use this weather API when an agent needs forecast temperature, conditions, wind, day/night periods, or detailed local forecast text for U.S. coordinates.

Look up a Base Mainnet transaction by hash and return pending/success/reverted status, confirmations, block number, sender, recipient, ETH value, gas usage, contract address, log count and explorer URL. Use for transaction verification, payment confirmation, receipt lookup or onchain monitoring.

Get a Base Mainnet wallet's current native ETH and USDC balances in one call. Use this blockchain endpoint when an agent needs a wallet balance, Base address balance, ETH holdings, USDC holdings, treasury check, payment balance check, or onchain account snapshot.

Get official U.S. SEC EDGAR company information and recent filings by stock ticker. Use this endpoint for company research, 10-K, 10-Q, 8-K and other filing discovery, CIK lookup, exchange information, fiscal year data, and direct SEC filing URLs.

Fetch any public URL and return a clean, readable markdown or JSON extract for AI agents. Pass the target as ?url=<encoded>. Ideal when you need to read webpages, docs, or articles without a browser. Blocks script/style tags, normalizes links and images, strips HTML.

Compare two Internet Archive Wayback snapshots near caller-supplied dates and return snapshot URLs and textual change evidence.

Compare a public webpage current text against caller-supplied prior text and report whether it changed.

Detect likely web technologies from a public page response headers and HTML signatures.

Fact-check verdict written by Claude Haiku 5.5 (Anthropic) from real web sources: supported/contradicted/mixed/unverifiable, each source with its stance (supports/contradicts/neutral). Answer in a fe…

Rank up to 50 documents by relevance to a query in a single call - each document returned with its relevance probability, sorted highest first. Powered by Jev (TypeSafe System One). $0.001 per call, …

Summarize a URL, raw text or HTML at the length you request - short, medium or long - with the source noted. Neutral and factual, no invented facts. Try GET /summarize/sample. Part of the AgentIndex …

Check whether a source supports, contradicts, or gives insufficient information about a claim - a typed verdict with a real probability, not generated text. Powered by Jev (TypeSafe System One). $0.0…

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…