Web Search Research x402 offerings

The rel="sponsored" links of a page: every matching <link>/<a> with href, resolved to absolute URLs, with a count. Ad disclosure. $0.01 per page.

The rel="stylesheet" links of a page: every matching <link>/<a> with href, resolved to absolute URLs, with a count. Link-relationship discovery. $0.01 per page.

The rel="terms-of-service" links of a page: every matching <link>/<a> with href, resolved to absolute URLs, with a count. Link-relationship discovery. $0.01 per page.

The rel="ugc" links of a page: every matching <link>/<a> with href, resolved to absolute URLs, with a count. User-generated content links. $0.01 per page.

The rel="webmention" links of a page: every matching <link>/<a> with href, resolved to absolute URLs, with a count. Link-relationship discovery. $0.01 per page.

Keyless attested web search (?q=) for agent grounding. $0.025 Base USDC — agent-search band. Ed25519-attested result set.

Keyless attested web scrape: ?url= → { title, markdown, word_count }. $0.02 Base USDC (agent scrape band).

Revisit up to three approved, rights-reviewed public text sources. Check exact quoted passages in versioned extracted text, compare declared prior text hashes and return bounded locators, retrieval times and hashes. No paywall bypass, PDF/JavaScript execution, factual certification or completeness guarantee.

Web search that returns READY-TO-USE grounding text, not links: for one query you get the passages an independent search index extracted from the pages it ranked, flattened into chunks with their source URL and title and an approximate token count, under a token budget you choose (1024-32768, default 4096). Use it to ground a model or a RAG pipeline in one call, where search + extract would take several.

Read the latest items from a public RSS or Atom feed now. Use for a one-session lookup.

You are ephemeral. longwatch remembers what you already saw. Create a watch, persist watch_id + key, poll later for only what you missed — pages, RSS, crypto prices, SEC filings. No API key, no account — pay per call in USDC.

Fetch any public web page or API and get it back as clean JSON — status, content type, final URL after redirects and the body as text, size-capped. The mid-task primitive agents use to read a doc, open a link or pull...

Filtered crypto and markets newswire for agents and research bots: headlines with source and timestamp, noise removed.

Research brief on any question: live web sources gathered, then an AI-written synthesis with key points and a cited source list. Ask in plain language — built for conversational agents and research bots.

What is the web saying right now? Live search results condensed into clean text for agent reasoning — answers beyond any model's training cutoff. Google-grade when the node's search provider is configured.

AI deep-dive on any supported asset: technicals, flows and narrative in one written analysis.

Summarize text in at most N sentences (1-8) in the language you choose, using only facts stated in the text with numbers kept exact. Built for agents that must shrink a page, email thread or filing before spending con...

Search live UK Parliament data: Members (current and former MPs and Peers, by name) and Bills (by title). The only sources used are the UK Parliament's own public Members API (members-api.parliament.uk) and Bills API (bills-api.parliament.uk), both unauthenticated. Votes and Divisions data (a different API family) is out of scope for this version.

Summarise text into a short, faithful summary (optionally in a target language and word limit).

Encyclopedia summary of a topic: title, one-line description, the lead paragraph as plain text, thumbnail and article link, in any language edition.

Use when you need what a web page says: read a public web page as clean text for an AI agent: title, description, main text (scripts, styles and navigation removed) and links. Respects robots.txt.

Turn a public web page into structured JSON for an agent: title, description, language, canonical URL, Open Graph and social tags, JSON-LD structured data, headings, link and image counts. Respects robots.txt.

Use when you need a web page as Markdown for a model: read a public web page as Markdown for an AI model: headings, lists, links and tables kept, scripts and styling removed. Respects robots.txt and follows up to 5 redirects. Output capped at 100,000 characters.

Use when you need to see how a page looks: screenshot of a public web page as rendered in a real browser (1280x800, or the full page), returned as base64 PNG: for visual checks, previews, or feeding a vision model. No free trial.