Web Search Research x402 offerings

Render any public URL in a real browser (Chromium): markdown text plus screenshot and evidence URLs. $0.005 USDC on Base per call.

Returns news articles about companies, filtered by company, search terms, category, source, language, publish date and expansion signal type. 25 per page. Each call is 3 credits.

Returns news signals for one company (domain_search_id from a lookup or search) over a date window: mention volume, top topics and sources, category and market breakdowns, and a weekly series. Each call is 3 credits.

Returns one news article by the news_search_id a news search returned: headline, summary, source, publish date, categories and the company. Each call is 1 credit.

Every link on the page as absolute URLs, with optional same-domain-only and visible-only filters.

The page's rendered content as Markdown.

One call, several formats: rendered HTML content and a base64 screenshot (plus optional Markdown and accessibility tree), with the page's status and title.

Read any public web page as clean readable Markdown for RAG and LLM pipelines — main article text with nav/ads stripped, plus title. The reader/scraper building block for agents. ?url=https://example.com&max_chars=20000

Web search: ranked results (title + url) for a query. ?q=x402+agent+payments&limit=8

Wikipedia article summary: description, plain-text extract and canonical url. ?title=Bitcoin

Web search: ranked results (title + url) for a query. ?q=x402+agent+payments&limit=8

Read any public web page as clean readable Markdown for RAG and LLM pipelines — main article text with nav/ads stripped, plus title. ?url=https://example.com&max_chars=20000

Searches question-and-answer content and returns relevant matches.

Fetch a public web page and return its title, description, clean Markdown (scripts, styles, nav chrome removed) and the list of links. No model call, deterministic.

AI Deep Read: fetches up to five pages, reads them, and synthesizes a sourced answer to your question via Workers AI. Input is capped for predictable cost. Pass urls=<comma-separated> and question=<your question>.

AI summary of any public webpage: fetches the URL, extracts readable content, and returns a short, medium, or long factual summary.

Get structured metadata for a public webpage: title, description, canonical URL, Open Graph fields, favicon, and language.

Extract clean readable text and metadata from a public webpage and return structured JSON for AI agents.

Bazaar Scout: searches the Coinbase Bazaar for a capability, live-probes the top candidates (still returning HTTP 402? how fast?), and returns a ranked shortlist with a best-value pick — a vetted result set, not a raw listing dump.

Search the Coinbase x402 Bazaar for paid resources by natural-language query.

Monitors search rank changes and trends for tracked terms.

Read a website's /llms.txt (the standard that tells LLMs what a site is about) as structured data: title, summary, sections with links and descriptions, and whether llms-full.txt exists.

Use when an agent needs what a page SAYS and not its HTML: it fetches one URL and returns the readable page as markdown - title, description, headings, paragraphs and links with their destinations, plus the canonical URL, language and word count. Boilerplate, scripts and navigation are stripped. Built for going through a list of links one at a time. No API key, no account.

Read web pages as clean text: pass ?urls=a.com,b.com (up to 10 in one call) and get each page title, meta description and readable body with script, style, nav and footer stripped, plus the final URL after redirects, the content type, the byte count and whether it was truncated. STATED PLAINLY BECAUSE IT CHANGES WHAT YOU ARE BUYING: this is a fetch, NOT a browser. JavaScript is not executed, so a page that renders its content client-side comes back thin or empty, and we say s