Web Search Research x402 offerings

Delivers a paid morning news briefing with public market and current events updates.

The Papers, full edition: every dated world event (Wikipedia), every AI model release and new software version since your training cutoff.

Multi-engine web search (metasearch). One search query fanned out across 2-3 search engines (Brave, Yahoo, Yandex) with results deduplicated by URL and merged by reciprocal-rank fusion: consensus ranking across engines instead of one engine's bias, with per-engine rank attribution on every result.

Run 2-5 web searches in one call with a 20% volume discount vs. individual searches. Each query returns ranked results (title, URL, snippet). Ideal for multi-faceted research or comparing sources on different aspects of a topic. If some queries fail upstream, the call returns the ones that succeeded with an error on each failed query and is charged; a call where every query fails is not charged, except a Tempo transfer sent before the call, which is recorded as owed.

Newest headlines from a deduped, tiered 972-feed direct portfolio (primary sources + wires/majors + trade press + Hacker News + gated GDELT), newest first, up to 100 per call — filter by category, source, and language; every article carries tier, categories, summary/author/image when present, and a provenance-labelled tone

One call, many sources: search Hacker News, GitHub, Stack Overflow, and Wikipedia by keyword and get back a unified, ranked result set — titles, URLs, scores/stars, and snippets — across all of them at once. The general research/search read agents make to ground answers, find code, surface discussion, and gather context. No API keys, no per-source accounts, free upstreams. Pass. List your own x402 service on bazaar.agentexchange.work/listings: 1 USD, 30 days, live at once, no account.

Summarize and classify a text (up to 4000 characters). POST a JSON body {"text": "..."}. The summary is written in the language of the input text. Categories: news, opinion, technical, commercial, other.

Fetch a web page and return clean Markdown with Litmus intelligence. Requires payment of $0.005 USDC per page.

Fetch a web page and return clean Markdown with Litmus intelligence. Requires payment of $0.005 USDC per page.

Nerf Radar: a structured summary of one official game patch (World of Warcraft: Forever (beta), World of Warcraft (Retail), Counter-Strike 2, League of Legends, VALORANT, Deadlock, Overwatch, Dota 2, Marvel Rivals, Apex Legends, Fortnite, Rainbow Six Siege, WARDOGS (early access), Teamfight Tactics, PUBG: BATTLEGROUNDS, Clash Royale, ARC Raiders, Helldivers 2 and Dead by Daylight), with a TL;DR, who it matters to, and every change labeled buff, nerf, adjust, new, removed or fix, with before and after values and the official source URL.

Ask a question, get a direct answer grounded in a live web search, with numbered citations (title, url, published_date). One call replaces search + read + summarize. For ranked results instead of a synthesized answer use /exa/search. Keyless x402, pay per call on Base or Solana.

Clean page text for up to 3 URLs in one call via Exa's index + live crawl — works on JS-rendered and bot-walled pages that direct fetch can't read. Returns title, author, published_date and text per URL, with per-URL status. Pairs with /exa/search (search → contents). No API key, pay per call on Base or Solana.

Extract web content from any page or PDF as clean Markdown — web page text, HTML to Markdown for any URL: strips scripts, nav, ads, and boilerplate while preserving headings, links, lists, tables, code blocks, and blockquotes; extracts the text layer from PDFs. Returns Markdown body, title, word count, and a quality grade. Web reader for article and main content. For JS-rendered or bot-walled pages a plain fetch can't read, use /exa/contents.

Exa neural web search for AI agents — POST or GET a query, get ranked live results (title, url, published_date, author, score) with optional highlight snippets. Filter by category (news, research paper, github, company, pdf, and more), domain include/exclude, and publish date. For a direct answer use /exa/answer. No API key, pay per call on Base or Solana.

Summarize text, articles or documents — condense raw text, Markdown, or a URL into a TL;DR plus key bullet points. Accepts raw text or a URL (fetched and extracted), enforces an input cap, and returns a clean structured summary so agents can compress documents and articles in one call.

Web search for AI agents — one query in, ranked live results out (title, url, published_date, author, score, optional snippets). Neural + keyword modes, category/domain/date filters. For a direct answer use /exa/answer. Keyless x402, pay per call on Base or Solana.

Query the Internet Archive Wayback Machine to check if a URL has ever been archived, get the closest snapshot to a given date, retrieve the most recent capture, and return archival history stats — so agents can access historical web content, verify past content claims, and recover deleted pages.

Summarize text, articles or documents — condense raw text, Markdown, or a URL into a TL;DR plus key bullet points. Accepts raw text or a URL (fetched and extracted), enforces an input cap, and return…

Neural (embedding-based) web search over a curated web index, which finds pages by meaning rather than keyword overlap. Use it when a keyword engine returns the wrong thing: conceptual questions, 'pages like this one', or niche technical writing. Returns up to 10 results with title, URL, published date and author. Complements the keyword web search rather than replacing it.

Live news search as clean JSON: recent articles ranked with title, URL, snippet, age, source and a breaking flag, with a freshness filter. Use it for current events and headlines where a general web index lags.

News search: latest news headlines on any topic from thousands of outlets, updated every 15 minutes. Use when an agent needs what happened in the last 1-7 days (companies, crypto, politics, sports, tech). Pass q (keywords). Returns deduplicated headlines with outlet, link, publish time and match score from the GDELT global news index, major outlets and Hacker News. 0.004 USDC/call; failed calls are free.

News search: latest news articles and headlines by keyword with title, url, source and published_at from our own index of about 100,000 English web articles a day (built from the GDELT Project, thousands of outlets, last 7 days, updated every 15 minutes) plus Hacker News. Category (business, tech, health, science, politics) filters by GDELT topic. Use for current events and topic monitoring.

News sentiment for a company, token, person or topic: finds up to 25 recent articles in our own news index (GDELT and Hacker News, last 7 days) and rates how the coverage reflects on the topic: overall label (very negative to very positive), a -1 to 1 score, positive, neutral and negative counts, 3 to 5 themes, a two-sentence summary and every article with its own sentiment, title, source, date and URL. For trading signals, brand monitoring and research agents.

Situation brief on a topic (RAG over fresh news): searches recent news, reads the top articles and synthesizes a short cited summary of what is currently happening plus key points. Cites only the retrieved articles (anti-hallucination).