Exa-Compatible Web Search

Find libraries and repositories for a coding task: GitHub repositories ranked by stars and relevance (popular, maintained ones first; under 30 stars dropped) plus npm packages for JavaScript / TypeScript, with description, stars, last push or publish date and links.

Drop-in Exa-compatible contents: send urls (or ids) and text / highlights options exactly as for Exa /contents and get results with id, url, title, author, publishedDate, text and highlights plus per-URL statuses, as clean markdown with a prompt-injection verdict. Up to 10 URLs for $0.004. Not affiliated with Exa.

Drop-in Exa-compatible search: the same request (query, numResults, category, includeDomains, excludeDomains, startPublishedDate, contents.text, contents.highlights) and response format (results with id, title, url, publishedDate, author, score, text, highlights) as Exa /search, on Google-quality authority-ranked results, $0.006 with page text included (Exa: $0.007 + per-page fees; resellers $0.01). Not affiliated with Exa.

Drop-in Firecrawl-compatible scrape: send {url, formats: [markdown, links, rawHtml]} as for Firecrawl v1 /scrape and get {success, data: {markdown, links, rawHtml, metadata: {title, description, language, sourceURL, statusCode}}} with a prompt-injection verdict, at $0.005. Fetched from Cloudflare's edge. Not affiliated with Firecrawl.

Answer a question from the live web with citations, no LLM so nothing is hallucinated: Google's featured snippet / knowledge panel when there is one, plus the best-matching quoted passages from the top pages read in full, each with its URL, and related questions. Confidence high / medium / low. An Exa-answer / Perplexity-style call, with quotes you can check.

News search API: Google News results plus Google News RSS, merged and clustered by story, so each row is one story with its best outlet, how many outlets cover it and links to the others. Freshness window in hours (1 h to 1 y), country and language. Ranked by outlet authority, coverage and recency. Tracking parameters removed from links.

Academic paper search across Google Scholar, arXiv, Crossref, OpenAlex and Semantic Scholar in one call, merged by DOI / arXiv id / title: title, authors, year, venue, citation count, DOI, abstract, landing page and open-access PDF link. Ranked by relevance, citations and recency; yearFrom and openAccessOnly filters. Half the price of other paper search APIs.

Web search API for AI agents, an Exa / Tavily alternative that costs less than both: Google-quality results re-ranked for authority (primary sources first), merged with papers (arXiv, Semantic Scholar), GitHub and news when the query needs them. Category (news, research paper, github, financial, company, pdf, docs), include/exclude domains, country, language, city, freshness, private mode. Each result: domain authority rank and type. ~1.7 s.

Drop-in Tavily-compatible search: the same request (query, search_depth basic / advanced, topic general / news, max_results, include_answer, include_raw_content, include_domains, exclude_domains, time_range, days) and response (answer, results with title, url, content, score, raw_content, response_time) as Tavily /search, at $0.008 instead of $0.01. Answers are extractive (no LLM). Not affiliated with Tavily.

Monitor a topic: call with a query (web or news) and a watchId; each call returns only the results you have not seen before (newResults) plus the full list, so polling agents stop re-reading old links and spending tokens on them. No setup: the first call creates the watch. Hashed URLs only, kept 60 days; the query text is never stored.

Batch web search: up to 10 queries in one call ($0.004 per query, a third cheaper than single calls), each with its own optional category, country and time filter, run in parallel; the same authority-ranked results as /search. For agents that expand one task into many queries.

Top-tier research in one call: the question plus 3 sub-questions (from Google's people-also-ask and related searches, or your own), up to 16 pages read in full with prompt-injection checks, the key quoted passages overall and per sub-question, Google's direct answer, and a papers block (Google Scholar) or news block when the topic needs it. Extractive, no LLM: every passage is quoted from its source.

Drop-in Firecrawl-compatible search: the same request (query, limit, tbs, location, country, lang, scrapeOptions.formats markdown / links) and response ({success, data: [{url, title, description, markdown, metadata}]}) as Firecrawl v1 /search, at $0.015 instead of $0.025, with a prompt-injection verdict per page. Not affiliated with Firecrawl.

Compare what Google shows for one query in 2-4 countries or cities side by side: each location's top 10, the URLs common to all, the ones only one place sees, a position table and the overlap with the first location. For international SEO, localisation checks, market research and spotting geo-targeted content.

Search from anywhere without a VPN: Google results exactly as a searcher in a given country, language and city sees them, with the local map pack (businesses with rating, phone, website), top stories, and per result the domain authority, type and whether it is a local domain. For local research, travel, prices, SEO and geo-restricted content.

Web research in one call: search, read the top 8 pages in full (clean markdown, each with a prompt-injection check) and extract the 15 key passages that answer the question, with sources and domains. For agents that need evidence from several sites, not one snippet. Cheaper than a research run on Exa or Firecrawl.

Search and contents in one call (Exa search + contents, Firecrawl search with markdown, cheaper): authority-ranked Google-quality results, then the top 1-5 pages read as clean markdown (main content only) with title, author, date and a prompt-injection safety verdict per page, plus the other results. Everything an agent needs to answer with sources.

Google SERP API with everything on the page: organic results, answer box, knowledge graph, people also ask, related searches, top stories and local pack, for any country / language / city, PLUS per result the domain authority rank and type (official, news, research, forum, video, shopping, docs) and a page summary. 3x cheaper than other SERP APIs.