Web Search Research x402 offerings

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

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).

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

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

One-stop research assistant: searches the web, fetches top results, and generates an AI-powered summary with key findings.

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.

Google Autocomplete suggestions for a partial query. Useful for keyword research and intent discovery.

Google Images search. Returns direct image URLs with dimensions, thumbnails, and source pages.

Read the structured data a page declares about itself: products, articles, events, organizations. The structured data a page declares about itself: every JSON-LD block parsed, the schema.org types found, and the Open Graph tags. Fetched through a residential IP with a real browser. No model in the path. Bo…

Send a URL and receive the page as a PDF document, rendered by a real Chromium browser exiting through a French residential IP. JavaScript runs before printing, so single-page applications and dynamically loaded sections appear in the output. Useful for agents that need an archivable, shareable record of a web page: a quotation, a legal notice, a listing or any document that must be kept exactly as it was published on a given day.

Get the full HTML of a page after its JavaScript has run, as a browser sees it. Send a URL and receive the complete HTML of the page after JavaScript execution, exactly as a browser would see it. The request goes through a French residential IP driving a real Chromium instance, which resolves single-page applications and gets past defences that block datacenter r…

Read the main content of a page your own crawler cannot reach, as clean markdown. Send a URL and receive the main content of the page as clean markdown, stripped of navigation, advertising and boilerplate. The page is fetched through a French residential IP with a real Chromium browser, so JavaScript-rendered content is fully resol…

Read a page and get a deterministic verdict on whether the retrieval can be trusted, with evidence. PRIVATE BET…

Every form on a page with its action, method and fields (name, type, label, required, options), so an agent knows what a page asks for before interacting. Read only: nothing is submitted. Body: {url}.

The document outline of a page: every heading with its level and anchor, in order. Body: {url}.

Get fresh headlines about a topic, with source and age. Fresh news search (Google News via Serper): latest headlines with source, date, snippet. Great for crypto/market/current-events agents. Query: ?q=&gl=&hl=

Search a topic and get the full content of the best pages, in one call. Search, then read the top results, in one call: ranked results from a real web search, and for each of the top pages its main content as markdown, read through a residential IP with a real browser. A page that could not be…

The document outline of a page: every heading with its level and anchor, in order. Body: {url}.

Turn every table on a page into JSON rows you can compute on. Every HTML table on a page as JSON rows, with headers detected and captions kept. Fetched through a French residential IP with a real Chromium, so tables rendered by Ja…

Every image on a page with its resolved URL, alt text and dimensions, plus the social preview image. Body: {url}.

Collect the emails, phone numbers and social profiles a page visibly publishes. Emails, phone numbers and social profile links visibly published on a page, read from the rendered DOM and mailto: and tel: links. Nothing is inferred, enriched or cross-referenced: only what the page itself shows. Body: {url}.

Get ranked web results for a query. Real Google web search: top 10 organic results, answer box and knowledge graph, in one call. STANDARD tier, a useful single-step result. Query: ?q=&gl=&hl=

Collect the emails, phone numbers and social profiles a page visibly publishes. Emails, phone numbers and social profile links visibly published on a page, read from the rendered DOM and mailto: and tel: links. Nothing is inferred, enriched or cross-referenced: only what the page itself shows. Body: {url}.

Tell whether a page changed since the last time you read it. Has a page changed since you last read it? Send a URL and the content_sha256 you kept from a previous call; get back changed: true or false, the current checksum and the current length. Without a checksum, returns the starting point. Main content only, navigat…