Web Search Research x402 offerings

Unblocker for AI agents: send {url} and get the page back as clean Markdown, with title, description, language, final URL and HTTP status. Gets through Cloudflare and other common bot protection and can render JavaScript-heavy pages. Set format to html or text for those instead. A page that can't be fetched (blocked, error status or empty) is not charged. No API key, proxy or account: pay per call in USDC over x402 (Base, Polygon) or MPP (Base).

Google Search results (SERP) for a query, as JSON. Each record is one results page with organicResults (position, title, url, displayedUrl, description), paidResults, relatedQueries, peopleAlsoAsk and searchQuery metadata. Body: {query, limit}. limit (1-20) is rounded up to whole pages of about 10 results, so 1-10 returns one page and 11-20 returns two. Useful for rank checks, source discovery and grounding answers in search results.

Google News search API for AI agents: send a keyword or phrase and get up to 30 current news articles as JSON: headline, publisher, publish time, a short description and the article's link. Choose the language and country edition. Articles you paid for but did not get are refunded.

Web search with page content for AI agents: send keywords and get the top results with each page read as clean Markdown, in one call: title, URL, a short description and the page's text. Up to 5 resu…

Search API for AI agents: web or news search with up to 30 results per call, each with a title, URL and a query-relevant excerpt. Filter by site, or by category: developer (repos, issues, docs), GitH…

Unblocker for AI agents: send {url} and get the page back as clean Markdown, with title, description, language, final URL and HTTP status. Gets through Cloudflare and other common bot protection and …

Google Search results (SERP) for a query, as JSON. Each record is one results page with organicResults (position, title, url, displayedUrl, description), paidResults, relatedQueries, peopleAlsoAsk an…

YouTube video search by keyword, or the videos of one channel. Mode search takes keywords; mode profile takes a channel handle without the @. limit is 1-20 regular videos, no Shorts or live streams. …

Google News search API for AI agents: send a keyword or phrase and get up to 30 current news articles as JSON: headline, publisher, publish time, a short description and the article's link. Choose th…

The grounded council: we buy the facts first, then deliberate on them. Your question is scanned for a contract address, URL or $TICKER; we spend on the matching evidence (honeypot simulation, sanctions screen, page content, SEC profile), hand it to one analyst that judges on what was found, not on recollection. The response lists every source and what we spent for you.

Check robots.txt, sitemap, Link headers, markdown access, llms.txt, and AI content-signal hints for agent-facing discoverability.

Fact lookup for grounding: best-matching Wikipedia article summary plus structured Wikidata facts (website, founding date, birth/death dates, population, coordinates) and the source link. Any language edition.

Extract structured JSON from any web page. Give a URL plus a JSON schema or a plain-English prompt describing the fields you want; a headless browser renders the page and an LLM fills the schema. Also callable as GET with the same fields as query parameters.

Observe whether one x402 seller resource appears in Coinbase Bazaar merchant discovery and where the exact resource sits in the first 20 results for 1–3 buyer-supplied job-language searches. Factual evidence only. Call when you need a point-in-time Bazaar presence and top-20 search observation, not a trust, SEO, or remediation score.

Fetch deterministic, token-efficient context from one public HTTPS URL: canonical URL, title/description, headings, clean main content, structured-data types, freshness observations, evidence, and limitations. Call when you need a bounded JSON reading of one public page without a browser, login, crawl, or LLM.

Groups managed news feeds into events when an agent needs a compact news briefing. Supply topic, language, time window and result limit using the published schema. Returns headlines, a short abstract, first-report time, reporting-source counts and citations. Coverage is limited to the managed feed set; source count is not independent confirmation. Third-party article bodies are never returned.

Groups managed news feeds into events when an agent needs a compact news briefing. Supply topic, language, time window and result limit using the published schema. Returns headlines, a short abstract, first-report time, reporting-source counts and citations. Coverage is limited to the managed feed set; source count is not independent confirmation. Third-party article bodies are never returned.

One page load answers everything an agent needs to reason about a page: the DOM after JavaScript capped at 2 MB, the CDP accessibility tree flattened with parent references, every link with rel and target and an internal or external verdict, every form field with its label and autocomplete hint, console errors and warnings with source and line, a screenshot, navigation timings and a summary of the requests the page fired. Chrome runs without credentials, without cookies and without login, so a s

Viewport or full page, optional element selector, dark mode and cookie banner removal. Returns base64 image plus a short lived fetch URL, byte size, load time and the final HTTP status of the page.

Summarize a text or a web page (LLM, word limit, key points) (1 × 5,000 characters at 0.040000 USDC each)

Tell me what changed on this page since my last check (deterministic, no LLM)

Fetch a PDF and extract its text per page, with the document info

Fetch a web page and extract clean text, title, description and links

Render any public web page in a real Chrome browser and return a PNG screenshot. Use when you need to see how a page looks, check a layout, capture visual evidence, or read content that only appears after JavaScript runs. Options: width 320-2560 (default 1280), full=true for the whole page. Errors: 400 bad or private URL, 504 page took over 30s.