web-search-and-content

Fact verification API for market data — cross-check a ticker against live provider evidence and return an evidence-backed result instead of guessing.

Web scraping and extraction credit pack for AI agents: 10 accepted public-URL clean-text reads at a micro-price with no scraper subscription.

Web scraping API for AI agents — extract clean text and metadata from one safe public HTTPS URL in a single x402 call.

Extract the full text of any PDF from a URL - no upload, no OCR setup, just pass the link. Returns plain text plus page count and word count as JSON. Built for agents reading research papers, filings, annual reports, datasheets and documentation. Handles files up to 25 MB.

Extract fresh structured JSON from a public webpage.

Web page extractor for AI agents: fetch any public URL and get clean Markdown, the page title and all links as JSON, with scripts, styles and menus removed. url is the page address (https://...). Private or internal addresses are blocked; pages over 2 MB or slower than 10 seconds are rejected and you are not charged.

Intelligent document summarization for any text document (reports, articles, emails, legal docs, code). Returns an executive summary, key points, keywords, sentiment, document type classification, and action items. Structured JSON output by

Precision JSON extraction engine. Feed messy raw text, HTML, or unformatted data plus your target JSON Schema, and get back a single valid JSON object that strictly conforms to it. Ideal for agent pipelines that need structured data from un

Extract structured JSON from any text using your field list (invoices, emails, contracts, listings) — Genesis402 / UnyKorn Operator Network

robots.txt parser: rules, sitemaps, AI-crawler blocks, and is-this-path-allowed check — Genesis402 / UnyKorn Operator Network

Link map: fetches one public HTML page server-side and returns up to 100 normalized, deduplicated http/https links with internal/external classification and counts, the final URL, a timestamp and a tamper-evident receipt. Single GET query parameter (url). One page only; no recursive crawling. Check crawl permission first with GET /api/v1/robots-check.

Text to JSON: Extract Data Without Guessing: Extracts data from text into JSON that matches the shape you give (a JSON Schema, an example object or a list of fields), without guessing. Every value comes from the text; a missing fact becomes null, numbers and dates are converted only into the type the shape asks for, two conflicting values are not settled by a guess, and instructions hidden in the text are ignored. Use when asked to extract structured data, turn text into JSON, parse an invoice,…

SQLite Search Builder: Builds or fixes a site or product search so it finds what the user meant, with SQLite full-text search (FTS5) on D1, Turso or SQLite. Word order, singular or plural, endings, case, punctuation and accents stop mattering ("cafe" finds "Café", "tomatoes" finds "tomato", "red tomato" finds "Tomato, red", "ab1042" finds "AB-1042"), and the start of a word is enough ("tom" finds "tomatoes"). Gives one normalize pipeline for accent-insensitive search, a query-side ending remove…

Deep research: sub-query decomposition → multi-engine search → page fetch → cited synthesis (extractive or GLM-LLM). $0.05.

Fetch a web page and return its readable text with scripts, styles, navigation and markup stripped, plus title and metadata.

Multi-engine web search: query decomposition (up to 5 variants), SearXNG 20+ engine fan-out, URL dedupe, diversity ranking, 5-min cache. $0.01.

Bulk URL-to-markdown research pack (1-25 URLs per call). Pairs with /v1/web-search: pipe results[].url straight in for LLM synthesis.

Verify a claim about a web page's content: fetches the page (SSRF-guarded) and reports whether the expected text appears, with the surrounding excerpt as evidence. The deterministic way for an agent to confirm 'the site says X' before acting on it. Use this when an agent needs to does this page actually say that? Checked, not guessed.

Fetch a web page server-side and convert it to clean markdown — headings, links, lists, tables and text, with scripts, styles and boilerplate stripped. The 'reader' pattern agents use to actually understand web pages. SSRF-guarded with redirects re-validated, 10s timeout, 1MB cap. Use this when an agent needs to fetch any page and get clean markdown an LLM can read.

Fetch a PDF (by URL, SSRF-guarded) or accept it as base64 and extract all readable text with page count. Deterministic parsing — no language model, so nothing is invented. Text-based PDFs only; scanned images need OCR (not included). Use this when an agent needs to extract readable text from any PDF — agents can't read PDFs.

Extracts OG tags, canonical URL, title, and meta description from any web page. Useful for link previews, SEO audits, and content enrichment.

Scrapes all images from the given URL. Extracts images from img, svg, picture/source, link, and video elements including inline SVGs, base64 data URIs, and standard URLs.

Web content extraction and search. Get clean markdown from any URL or search results.

Fetch Web Page as Text: fetch any public URL as clean readable text Executed deterministically by the AmanChain node against live consensus state (real blocks, pools, balances) — paid per call via x402, settled in USDC on Base. Input: JSON body {"serviceId":"aman-web-fetch","request":" "}. No account, no API key.