Search & web

Keyword and topic extraction from a page: the top 20 terms and top bigrams by frequency (stopwords removed), title and description for context. What is this page about, in one call. $0.01 per page.

FAQ extraction: question/answer pairs from schema.org FAQPage data, <details>/<summary> blocks, and headings phrased as questions with the paragraph that follows. Build knowledge bases from support and product pages. $0.01 per page.

Wikipedia search: the top 10 matching articles with title, snippet, word count and URL. Find the right article before pulling a summary. $0.01 per search.

Does a page contain a phrase? Fetches the page and searches its readable text (case-insensitive) for the phrase you give, returning found/not found with a snippet of context and the match count. Stock alerts, price wording, 'sold out' checks and content verification. $0.01 per check.

Hacker News search (Algolia): top 15 stories and comments matching a phrase, with points, comment counts, author, date and links, sorted by relevance. Find prior discussion of any topic or product. $0.01 per search.

HTML tables to JSON: every table on a page as arrays of rows (header row detected, cells cleaned of markup), with row and column counts and a caption. Pull structured data out of any web page. $0.01 per page.

Bullet and numbered lists from a page as arrays: each list with its items (cleaned text, up to 50 per list), ordered/unordered type and a preceding heading when detectable. Turn feature lists, steps and specs into data. $0.01 per page.

Price extraction from a page: every currency amount in the text and in schema.org/Open Graph price tags, with currency, numeric value, min/max, and product price hints. Price monitoring and catalogue scraping. $0.01 per page.

Date extraction from a page: the published and modified dates from meta tags and schema.org, plus dates found in the text (ISO, US and long forms), the earliest and latest, and a best guess at the publication date. Content freshness and timeline building. $0.01 per page.

Main image of a page: the Open Graph / Twitter image when declared, else the largest content image by declared dimensions, with alt text, resolved URL, content type and byte size via a HEAD request. Get a representative thumbnail for any URL. $0.01 per page.

Site navigation extraction: links inside <nav>, header menus and elements with menu/nav roles, deduplicated with their text, grouped as internal or external, plus a guess at the primary sections. Understand a site's structure in one call. $0.01 per page.

Footer link extraction with classification: privacy policy, terms of service, cookie policy, contact, careers, about, press, status page, social profiles, app-store links and everything else found in the page footer. Compliance and contact discovery. $0.01 per page.

Sitemap URL list: fetches sitemap.xml (or the URL you give), expands sitemap indexes up to two levels, and returns the page URLs (up to 500 shown), total count, sitemaps visited and lastmod range. Crawl planning and site inventory. $0.01 per site.

Named-entity candidates from a page without an LLM: capitalised multi-word phrases ranked by frequency, split into likely people (two or three capitalised words), organisations (with Inc, Ltd, University, Corp, Foundation...), places (after in/at/from) and other proper nouns, plus years and money mentions. $0.01 per page.

Readability of text you send: Flesch Reading Ease, Flesch-Kincaid grade, average sentence length, syllables, difficulty label and reading time. Check generated copy before publishing. $0.01 per call.

Structured data extractor: every JSON-LD block on a page parsed, with the schema.org types found (Organization, Product, Article, FAQPage, BreadcrumbList, LocalBusiness...), key fields (name, price, rating, author, date) and microdata/Open Graph hints. Rich data without scraping the layout. $0.01 per page.

Page weight and resource inventory from the HTML: document bytes, script/stylesheet/image/iframe/font counts, inline script bytes, external hosts contacted, and a simple heaviness verdict. A quick performance smell test without a browser. $0.01 per page.

Book search across Open Library: up to 10 results with title, authors, first publish year, edition count, ISBNs and cover. Find the right edition or reading list fast. $0.01 per search.

Wikipedia summary: the lead paragraph, short description, thumbnail, page URL and coordinates for a topic, resolving redirects and falling back to search when the exact title does not exist. Quick grounded facts for any agent. $0.01 per lookup.

AI-crawler policy of a website: reads robots.txt and reports, for 20 known AI/LLM crawlers (GPTBot, ChatGPT-User, OAI-SearchBot, ClaudeBot, anthropic-ai, CCBot, Google-Extended, Applebot-Extended, PerplexityBot, Bytespider, Amazonbot, cohere-ai, meta-externalagent and more), whether the root is allowed, blocked or unmentioned, plus an overall stance (open / selective / blocks-all-ai) and TDM/ai.txt hints. $0.01 per domain.

Search the x402 Bazaar (Coinbase CDP discovery index) for paid APIs other agents sell: full-text/semantic query returning up to 20 resources with URL, description, price in USDC, network, payTo, scheme, last-updated and input hints. Optional network filter after a pipe. Lets an agent find a capability to buy in one call. $0.01 per search.

Agent discovery card fetch: looks for /.well-known/agent.json and /.well-known/agent-card.json (Google A2A Agent Card) plus /llms.txt and /.well-known/ai-plugin.json, and summarises whatever is found: name, description, url, version, capabilities (streaming, push), skills (id, name, description, tags), auth schemes, input/output modes, and provider. Lets agents learn what another agent offers. $0.01 per domain.

JSONPath extraction: evaluates a path like $.store.book[*].author, $..price, $.items[-1], $['key with spaces'] against a JSON document and returns all matching values with a count. Handles recursive descent, wildcards, negative indexes and bracket keys. $0.01 per query.

Is a specific bot allowed to fetch a URL? Fetches the site's robots.txt and evaluates the path for the named user-agent (GPTBot, ClaudeBot, Googlebot, Bingbot, CCBot, PerplexityBot or any token), returning allowed/disallowed, the matching rule and group, crawl-delay, and whether the bot has a dedicated group or falls back to *. Pre-flight for compliant scraping agents. $0.01 per check.

Sitemap validator: fetches a sitemap or index, checks well-formedness, namespace, type (urlset/sitemapindex), counts entries, validates loc URLs (absolute, same host, no duplicates), lastmod formats, changefreq/priority values, the 50,000-URL and 50 MB limits, gzip, and lists the first errors. Returns valid true/false with error and warning lists. $0.01 per sitemap.

OpenID Connect discovery for an issuer: fetches /.well-known/openid-configuration and summarises issuer, authorization/token/userinfo/jwks/end-session/registration endpoints, supported scopes, response types, grant types, PKCE methods, signing algorithms, claims and subject types. Integration pre-check for auth agents. $0.01 per issuer.

Image inventory for a page: every image with resolved URL, alt text, declared width/height and lazy-loading, plus counts of missing or empty alt attributes (an accessibility and SEO issue). $0.01 per page.

HTML to plain text: strips tags, scripts and styles, decodes entities, keeps paragraph and line breaks, and returns word count. Clean up scraped or generated HTML. $0.01 per call.

Scrape a website page: fetches the URL and returns the page content as clean Markdown plus title, description, headings, word count and all links (URL and anchor text). Web scraping for agents without a browser, API key or proxy; handles redirects and strips navigation, ads and scripts. $0.01 per page.

$0.0002/call. Get an image's dominant color as hex/RGB — theming and palettes from any picture. 1¢ x402 min; remainder auto-credits — relaystation.ai/penny