Web Search Research x402 offerings

Extrae el contenido de una URL y lo devuelve limpio en Markdown/HTML para el contexto de un LLM.

Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; markdown or text output. Robots-respecting, public content only — the reader/scraper building block for RAG and agent pipelines.

Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; markdown or text output. Robots-respecting, public content only — the reader/scraper building block for RAG and agent pipelines.

Fetch any public web page and return its main readable content as clean Markdown or plain text plus metadata (title), stripping nav/ads/boilerplate (trafilatura). Optional JS rendering via headless browser for SPAs; markdown or text output. Robots-respecting, public content only — the reader/scraper building block for RAG and agent pipelines.

Parse an RSS, Atom or JSON Feed URL into a normalized item list (title/link/published/summary/id/author) plus feed-level metadata.

Extract every link from a public page for crawling agents: de-duplicated absolute URLs with anchor text, internal/external counts, declared feeds and a sitemap hint.

Keyword news search across web news engines (Bing/DuckDuckGo/Yahoo via ddgs). Returns dated headlines with title/url/snippet/source/image + freshness/region/safesearch filters.

Keyword news search across web news engines (Bing/DuckDuckGo/Yahoo via ddgs). Returns dated headlines with title/url/snippet/source/image + freshness/region/safesearch filters.

Deep version of the web page brief: crawls up to 3 same-domain pages, uses the larger model, and returns a more thorough evidence-backed report with more claims and key points. Versión profunda del informe web: rastrea hasta 3 páginas del mismo dominio, usa el modelo grande y devuelve un informe más completo, con más afirmaciones evidenciadas y puntos clave.

Turn a web page URL into a structured, evidence-backed brief: clean content summary, key points, named entities, sentiment, and claims each quoted with its evidence and source URL. Convierte una URL en un informe estructurado con evidencia: resumen del contenido, puntos clave, entidades, sentimiento y afirmaciones, cada una con su cita textual y su URL de origen.

Fetch URL content as Markdown: read any web page and get clean Markdown - navigation, ads and boilerplate stripped, links resolved, plus a real token count. The same extraction /search uses on result pages, exposed standalone for a URL you already have. Try GET /web-read/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Use this when the answer is outside SWOGE data: news, projects, teams, people, anything on the open web. Price: $0.01 in USDC on Base or Solana, or $0.02 in USDG or $SWOGE on Robinhood Chain (tool pr…

Fetch a URL and extract clean main-content text with title, description, word count, and char count; boilerplate (nav/footer/sidebar/ads) is stripped.

Extract page metadata: title, description, keywords, author, published/modified dates, canonical, language, favicon, and OpenGraph/Twitter card tags.

Fetch a URL and extract clean main-content text with title, description, word count, and char count; boilerplate (nav/footer/sidebar/ads) is stripped.

Extract page metadata: title, description, keywords, author, published/modified dates, canonical, language, favicon, and OpenGraph/Twitter card tags.

Extract structured elements: heading hierarchy (h1-h6), lists, tables as 2D arrays, and images with alt text, plus element counts.

Free-text web search for AI agents: ranked title/url/snippet results fused across multiple engines (Brave, Google, DuckDuckGo, Mojeek, Startpage, Yahoo), with freshness filters (past day/week/month/year), region/locale and SafeSearch. One call for grounded, up-to-date web results — no keys, no scraping setup.

Free-text web search for AI agents: ranked title/url/snippet results fused across multiple engines (Brave, Google, DuckDuckGo, Mojeek, Startpage, Yahoo), with freshness filters (past day/week/month/year), region/locale and SafeSearch. One call for grounded, up-to-date web results — no keys, no scraping setup.

Live web search for AI agents as clean JSON: up to 10 ranked results with title, URL, snippet and published date for any query — current events, facts, docs, companies, products, prices. Grounding and research in one call, no API key, no account, pay per search in USDC. Failed or empty searches are not charged. $0.01 per search.

Jev-routed web search: each query goes to the best specialised source (code, facts, news, prices), results ranked by relevance. 28/30 test queries answered. Up to 10 results per query, each with title, URL, snippet, short extract and publish date. Up to 5 queries per call, merged and de-duplicated. No account, no API key. Try GET /search/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Discover and parse a site's sitemap: pass a site root (found via robots.txt or /sitemap.xml) or a direct .xml. Returns URLs with lastmod/priority; handles <sitemapindex> (one level).

Structured parse of a public web page: main text, headings, links, tables and rich metadata (description, canonical, lang, Open Graph, Twitter cards, JSON-LD) as separate fields. Browserless, robots.txt-respecting.

Fetch a URL and return link-preview metadata from Open Graph, Twitter Card and standard meta tags.