Web & Data

Retrieve a real EVM transaction and normalized block, sender, recipient, nonce, value, gas, fee, type, and input fields by hash.

Validate declared signature status, freshness and payload evidence

Scans every US stock that also trades as a 24/7 synthetic perp and returns the gap: official (delayed) price, prev close, perp mark and oracle, funding APR, open interest, and computed `basis_percent` + `basis_vs_prev_close_percent` — the implied overnight move while the US market is shut. Widest dislocation first, plus a plain-English `reading`. `?limit=`, `?min_basis=`. From x402stock

Compare a bounded passage in the public-domain BSB and WEB without blending or interpreting the source texts.

Checks whether a domain appears technically configured for email delivery, from direct public DNS records only: MX presence, SPF presence, DMARC presence and policy, and an optional DKIM selector check. Queries DNS over HTTPS against a public resolver -- no test emails sent, no mailbox existence verification, no personal data, no leaked-email databases, no proprietary deliverability dataset.

Check a specific dataset, paper, repository, or model URL against the indexed open-science corpus and receive a conservative, source-linked commercial-use and redistribution status. Never infers permission from an absent or ambiguous licence -- returns unknown rather than guessing.

Search live drug and medicine metadata from the U.S. FDA's openFDA API: brand/generic name, active ingredients with strength, dosage form, route, manufacturer/labeler, product type, marketing status, and NDC codes -- plus an optional short (~400 character) label excerpt (purpose or indications only) and an optional recall/enforcement flag. Composed entirely from openFDA's NDC Directory, Drug Label, and Drug Enforcement APIs, all public domain (CC0 1.0 Universal). Never returns full label section

Joins caller-supplied vote vectors by proposal ID, encodes against/abstain/for as -1/0/1, and computes weighted cosine similarity plus exact agreement. It describes only supplied overlapping votes and does not infer ideology or future behavior.

Country reference data: capital, region, population, area, currencies, languages, calling code, timezones and borders

Bluesky (AT Protocol) public data: an account's profile plus recent posts with engagement counts, or a keyword post search

Hacker News full-archive search: stories, comments, Show HN and Ask HN with points, comment counts and URLs

Fediverse posts: search any Mastodon instance or read its public timeline, with author, engagement and hashtags

Fetch a URL and return its main content as clean Markdown (boilerplate stripped)

What is the actual answer to this question, according to the live web right now? Runs a multi-engine search, reads the top pages, and returns one synthesised answer with inline [1][2] citations and the source URLs behind them — the whole search-read-summarise loop in a single paid call instead of a dozen

Crawl a site from a start URL (same-domain, breadth-first) and return each page as clean Markdown

Turn messy text — or any URL's page content — into structured JSON matching the shape you ask for, so an agent can consume a web page as data instead of prose

Fetch up to 10 URLs concurrently and return each as clean Markdown (bulk rate)

Web extraction for AI agents: URL to clean Markdown + metadata, automatic JS rendering, robots.txt respected. No API key.

Query verified x402 & agent-economy intel: facilitator quirks (PayAI v1/v2, EIP-3009 gas-free), discovery registries (bazaar index-on-settle, no-KYC), USDC-on-Base gotchas, live agent income channels. Returns ranked fact snippets for agents building on x402.

LLM Chat: Chat with a language model. OpenAI-compatible /v1/chat/completions interface. Supports 50+ models. Free models (auto, eco, premium) are $0 — paid models (gpt-5.2, claude-opus-5, deepseek-v4-pro, ...) are charged at cost. See /tools/llm_chat/models for the full model list and rates. Pay per call in USDC on Base via x402 — POST https://x402.freeq.one/tools/llm_chat.

A full Markdown report on a topic you specify, researched on the live web at the time of the request, with every source linked. As long as the topic needs, never cut short. Typically 2-4 minutes; allow 360 s before giving up. POST {"topic":"..."}.

Computes a SHA-256 digest of any input text and returns it as a hex string, computed locally with no network round-trip to a third party. Also supports SHA-512, SHA-1, and MD5 on request. Useful for content fingerprints, cache keys, and deduplication logic where the same input must always produce the exact same output.

Returns the exact current time in any IANA timezone, local ISO timestamp, UTC equivalent, unix epoch, human-readable string, and day of week, computed live rather than estimated from training data. For agents coordinating across regions or logging events with an authoritative timestamp.

Breaks down any text into character, word, and sentence counts, estimated LLM token count, and reading time, computed instantly with nothing stored. Useful for context-budget checks before an API call, content-length validation, and editorial word-count requirements.