Web Search Research x402 offerings

Deep verify. Use when a claim is high-stakes, or when Check answer or Extract claims marks it unsure (next_step). Checks it against Wikipedia, Wikidata, Google News, Europe PMC studies, FRED economic data and SEC EDGAR filings, and flags contradiction when sources disagree. Async: returns a job_id; poll GET /v1/jobs/{id} free for verdict, evidence for and against, citations. $0.75 USDC.

Verify claim. Checks one factual claim against public sources (Wikipedia) and returns a verdict (supported, contradicted, outdated, mixed or insufficient_evidence) with confidence, a short reason, the quote and source URL, and a receipt. $1.00 USDC.

Check whether a source supports, contradicts, or gives insufficient information about a claim - a typed verdict with a real probability, not generated text. Powered by Jev (TypeSafe System One). $0.001 per call, no OpenRouter or TypeSafe account needed. Try GET /verify/sample.

Render a web page and return its content as markdown

Render a web page and return its content as markdown

Multi-source web research and company/topic intelligence: runs a live web search, visits the top sources, and returns ranked results with titles, URLs, and content snippets. One call replaces a search-then-scrape pipeline for deep research agents.

Headless browser rendering for JavaScript-heavy pages and SPAs: full stealth Chromium render, then clean markdown plus title, meta description, and canonical URL. Use when a plain fetch returns an empty shell or a bot wall.

Structured data extraction returning typed JSON from 17 specialized site extractors: Twitter/X, GitHub, CoinGecko, Hacker News, YouTube, Wikipedia, npm, PyPI, crates.io, Product Hunt, IMDb, Amazon, Crunchbase, SEC EDGAR, Zillow, Redfin, and news articles. Auto-detects the right extractor from the URL — no scraping selectors required.

Live web and X research with cited factual findings for any query.

Ask a question about any public PDF and get a cited answer - pass a PDF URL and a plain-language question; returns the answer, confidence, verbatim supporting quotes with page numbers, or not_found. PDF question answering, document QA, read a filing/paper/manual/contract for me, extract a fact from a PDF. Text-based PDFs up to 25MB (no OCR). Full text instead: /pdf/text $0.01.

Extract clean Markdown from any URL. Renders JavaScript before extraction.

Web search for AI agents. Ranked results with page passages already extracted, plus URL to markdown.

Wire headline digest — live RSS plus persisted Lounge feed with optional category filter

Full-text search across every aggregated data source in one call: news, SEC filings, court opinions, academic papers, government records, and developer discussions. One query surfaces everything conc…

One call, every category: pulls everything matching a topic across all aggregated sources and groups it by category (news, legal, academic, dev community, ...) with counts -- replaces manually callin…

Prompt injection scan and content security check before an agent INGESTS external content (SKILL.md, web page, user input, tool output): detects prompt-injection, data exfiltration, dangerous code execution, hidden/invisible unicode and instruction overrides — 0-100 risk score + SAFE/WARN/BLOCK verdict + structured findings with matched evidence. A fast, cheap, deterministic pre-ingest firewall / skill-audit / untrusted-content security check for AI agents.

Extract and classify all hyperlinks from a web page — internal vs external using eTLD+1 domain matching. Returns up to 200 internal and 200 external links with counts. No web crawler setup needed. Accepts USDC payments on Base and Solana

URL-to-Markdown web extraction and context compression for AI agents. Fetch a public web page and return clean, task-relevant, citation-verifiable LLM context with exact excerpts, locators, hashes, and estimated tokens saved. Use before an agent summarizes, answers questions from, or cites a long or noisy URL. Deterministic and model-free. Public HTML only; no PDFs, logins, or JavaScript-only pages.

URL-to-Markdown web extraction and context compression for AI agents. Fetch a public web page and return clean, task-relevant, citation-verifiable LLM context with exact excerpts, locators, hashes, a…

Convert webpage to markdown: fetch any URL and return clean Markdown for LLMs and agents, with title, meta description, headings outline, word count, links and images. Navigation, ads, scripts and boilerplate are stripped, keeping the main article content. No API key. $0.01 per page.

Bulk convert webpage to markdown: up to 20 urls in one call, processed concurrently, results returned in input order with a per-item error field and a count of failures. Same answer per item as the single /convert-webpage-to-markdown endpoint (Convert webpage to markdown). Batch enrichment for agents that hold a list. $0.10 per batch.

Change watch for convert webpage to markdown: runs the check and compares it with the result from your previous call for the same url (kept 90 days), returning the current answer, changed true/false, exactly which fields changed with before/after values, and when it was last seen. Call it on a schedule to be told when convert webpage to markdown changes. $0.02 per check.

Is a claim independently corroborated across multiple unrelated sources, or does it trace back to a single origin? Groups matches by SOURCE (not category) so a caller sees exactly how many independent outlets/agencies back a claim -- a trust signal no single-source competitor can offer, since it requires already owning many independent sources.

How many <a> elements does the page have? Fetches the URL and counts a tags (plus, where relevant, how many have alt/src/href/type attributes), and the page's total element count for scale. Structural audits and template comparisons in one number. $0.01 per page.