Web & Data

Check whether a source supports, contradicts, or gives insufficient information about a claim - a typed verdict with a real probability, not generated text. Try GET /verify/sample.

Ask up to 20 typed yes/no, multiple-choice or ordinal-scale questions about one shared piece of context in a single call - each answered with a real probability (Jev decision primitives), not generated text. Powered by Jev (TypeSafe System One). $0.001 per call, no OpenRouter or TypeSafe account needed. Try GET /decide/sample.

Rank up to 50 documents by relevance to a query in a single call - each document returned with its relevance probability, sorted highest first. Try GET /rank/sample.

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.

Ask any factual or market-research question. Searches the live web with Tavily and Exa, extracts the most relevant page with Firecrawl, and returns a short synthesized answer with source URLs. Typical response 4 to 8 seconds. If it cannot answer in time you get an error and are not charged.

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

Geolocate an IP address. Returns country, city, ISP, coordinates.

Quick HEAD check on a URL. Returns status code, redirects, server info.

Check robots.txt rules for a URL. Returns allowed/disallowed, crawl delay, si...

Get HTTP response headers for a URL, including security header analysis.

Long or short bias per market with a score and the reasons behind it: funding, open interest and whale positioning combined. Heuristic, not advice

Where notional is entering or leaving each market over 1h/4h/24h, plus stealth accumulation: open interest climbing while price stays flat

Extract a public PDF (by HTTPS URL or base64) into clean Markdown - headings and tables preserved via layout-aware parsing, plus title/author/page count/date metadata and a real token count. Text content itself is never generated or altered, only its structure is inferred. Try GET /pdf/sample. Part of the AgentIndex content kit (pdf, web-read, extract, summarize, detect-language) - see GET /capabilities.

Get current time in multiple formats: Unix, ISO 8601, RFC 3339, human-readable.

Summarize text using local LLM. Supports bullet, paragraph, tldr, and structu...

Search the web and return structured JSON results. Aggregates 20+ search engi...

Extract text from images using OCR (Tesseract). Accepts base64 or URL input.

Extract text from PDF documents. Accepts base64 or URL input.

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

WHOIS registration data for any domain.

Extract all hyperlinks from a web page. Returns internal/external classificat...

Extract clean markdown from any URL. Full JS rendering via Playwright available.