Check an IP address against 15 major DNS blacklists (Spamhaus, Barracuda, SORBS, etc.) simultaneously — returns which lists it appears on, a reputation score, and a threat classification so agents can make block/allow decisions instantly.

IP geolocation lookup (geoip / IP location API) — geolocate any IPv4 or IPv6 address to city, region, country, latitude/longitude, timezone, and ISP/ASN as structured JSON so agents can localize content and enrich user records without a paid geolocation subscription. For proxy/VPN/anonymizer or hosting/datacenter detection, use /ip-risk/score or /ip-reputation/analyze.

One premium call returns a complete five-part IP profile — geolocation, ASN/network ownership, multi-DNSBL blacklist status, threat reputation, and an aggregate risk verdict — run concurrently with graceful partial-failure handling, so agents get a full IP workup and a block/allow decision in a single request.

IP reputation and malicious-IP check — screens an address against AbuseIPDB and AlienVault OTX threat feeds and returns a composite risk score, threat categories, malware families, and full source data.

One call returns a complete risk profile for an IP address — geolocation, ASN/network owner, blacklist status across multiple DNSBLs, and proxy/VPN/hosting classification — aggregated into a single verdict so agents can make a block/allow decision without calling four separate IP endpoints.

Repair malformed JSON into valid JSON — fixes code fences, trailing commas, single quotes, unquoted keys, bad escapes, duplicate keys, truncation, and JSON buried in prose. A deterministic tokenizer runs first (no LLM cost), with an optional Haiku fallback, plus optional schema validation and type coercion — so agents can rescue broken model output or dirty data in one call.

Decode and inspect any JWT token — extracts header algorithm, payload claims, expiry status, issued-at time, audience, issuer, and subject without requiring the secret — so agents can debug auth issues, check token expiry, and extract identity claims from tokens in pipelines.

Detect the language of any text input using stopword-set matching and Unicode script analysis — returns the detected language, ISO code, a high/medium/low confidence level, and top alternative languages so agents can route multilingual content, trigger translation workflows, and classify text without a paid NLP API.

Convert messy HTML or text into clean, well-structured Markdown using Claude Haiku — strips boilerplate, fixes heading hierarchy, normalizes lists and links, and returns readable Markdown so agents can feed clean docs into downstream pipelines, knowledge bases, or LLM context.

One-call market briefing for agents — BTC/ETH/SOL spot + 24h moves, major fiat crosses (USD/EUR, USD/GBP, USD/JPY, EUR/GBP), Base and Ethereum gas with USD transfer cost, and the crypto fear/greed index. Four sections fetched concurrently with graceful partial failure; any dead section is null with a finding, never a failed call. 60s cache; no API key.

OpenAI-compatible chat completions over x402, answered by Claude Sonnet 4.6 — send a messages array and get an assistant reply for Q&A, reasoning, agent planning, coding help, summarization, extraction, and classification. Body is OpenAI chat.completions-shaped ({model?, messages:[{role,content}], max_tokens?, temperature?}); response is a chat.completion object. Flat $0.06; inputs capped ~6KB, max_tokens 1024; no streaming in v1.

Normalize any messy money string into a typed decimal amount plus ISO 4217 currency — handles symbols, locale separators ($1,234.56 vs €1.234,56), magnitude suffixes (1.2M), accounting notation, and natural-language amounts — so agents can clean money values before converting or storing them, with no external data and a deterministic fast path.

Generate brandable startup/product names from a keyword using prefixes, suffixes, blends, and phonetic patterns, then check .com (or any TLD) availability for each via DNS — returns available names ranked by a brandability heuristic so agents can find a claimable brand without manual brainstorming plus one-by-one availability checks.

Conform messy or inconsistent JSON to a target schema using Claude Haiku — renames keys, coerces types (string→number, "true"→boolean, etc.), and fills missing fields with null, returning JSON that matches the exact shape the caller specified so agents can normalize data from varied sources into one consistent structure.

Fetch metadata for any npm package — download counts, latest version, version count, dependency/devDependency counts, maintainers, repository URL, license, and a health score based on maintenance signals — so agents can evaluate dependencies, audit package ecosystems, and assess supply chain risk. (Returns counts, not the full version/dependency lists.)

Fetch any public URL and extract structured metadata — Open Graph tags, Twitter Card tags, canonical URL, title, description, favicon, article author/date, JSON-LD structured data, and content type — so agents can preview, classify, and enrich links without building their own scraper.

Call OpenAI's gpt-4.1 via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.09 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-4.1-mini via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-4.1-nano via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-4o via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.10 per request in USDC. Standard OpenAI chat.completions shape. EVERY call is bounded by a 16000-token combined input budget (real tokenizer) plus the 48000-char cap; output 2048. Vision: up to 4 https image_url parts (detail low/high/auto).

Call OpenAI's gpt-4o-mini via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.1 via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.15 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.2 via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.20 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.4 via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.25 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.4-mini via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.04 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.4-nano via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.5 via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.65 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.6-luna via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.06 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.6-sol via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.65 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.6-terra via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.25 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5-nano via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Fetch any article or web page and extract clean readable text stripped of navigation, ads, and boilerplate — returns the main content body, word count, estimated reading time, detected language, and key sentences so agents can read the web without a browser or third-party scraping service. For JS-rendered or bot-walled pages a plain fetch can't read, use /exa/contents.

Parse and validate any phone number in any format, identify its country and line type (mobile/landline/VOIP/toll-free/premium for NANP + UK numbers; other countries return line_type unknown), and return all standard format variants (E.164, international, national) — catches fictional/unassigned NANP numbers (555 area code, 555-01XX range) so agents can validate contacts and normalize phone data without a paid telecom API.

Full detail for ONE Polymarket prediction market by id or slug — question, description, every outcome with its current price (implied probability), volume, liquidity, open/close dates, resolution source, category, and status. No API key. The drill-in companion to /prediction/markets (browse/search): find a market there, then pull its full state here. Pass id or slug as query (GET) or a JSON body (POST).

Live prediction-market odds from Polymarket — list the top active markets by volume, or search by keyword. Each result has the question, outcomes with current prices (implied probabilities), 24h/total volume, liquidity, and resolution date. No API key. Great for agents tracking real-world event probabilities (elections, crypto, sports, econ). Pass params as query (GET) or a JSON body (POST).

Follows a URL through its full redirect chain (up to 20 hops), recording status codes, timing, headers, TLS status, and protocol downgrades per hop, then returns an overall redirect health grade (A–F).

Fetch and parse a domain's robots.txt file — returns all crawl rules by user-agent, sitemap URLs, crawl delay settings, and checks whether a specific path is allowed or blocked for any bot — so agents can respect crawl policies and locate sitemaps before scraping.

Fetch and parse any RSS 2.0 or Atom feed URL and return structured articles with title, link, description (truncated to 500 chars), author, publish date, and categories — so agents can monitor content sources, build news pipelines, and process any feed without building their own XML parser. A URL that isn't a parseable feed still returns 200 with feed_type:"unknown", empty items, and a parse_failed finding.

Extract structured data from any unstructured text into your own JSON Schema — structured-data / information extraction, text-to-JSON, LLM data enrichment. You supply the schema; the LLM returns a matching object. Works for contacts, invoices, events, product specs, medical records, legal clauses, resumes — any shape. Returns the extracted object plus token usage; unfound fields are omitted or null.

Transform a source object into a target schema — matches fields by alias and structure deterministically, uses an LLM only for semantic mapping when needed, and supports mapping hints, transforms, and defaults, so agents can reshape data between systems with per-field confidence and a clear report of what mapped and what didn't.

Validate data against a supplied schema — checks required fields, nested objects, arrays, enums, string formats, numeric ranges, lengths, and additional-property rules deterministically, with optional type coercion and repair, returning precise errors with JSON paths so agents can verify structured data before acting on it.

Fetches a URL and evaluates 10 security-critical response headers (CSP, HSTS, X-Content-Type-Options, X-Frame-Options, Referrer-Policy, Permissions-Policy, X-XSS-Protection, CORP, COEP, COOP), detects anti-patterns, and returns an overall security grade (A–F).

Semantic similarity ranking — send a query plus up to 100 candidate texts, get the candidates back ranked by semantic similarity with scores. No vectors, no cosine math, no embedding model to manage: one call, one price, ranked results. Flat $0.02 per call in USDC via x402, no API key. For RAG retrieval, FAQ matching, and search result ordering.

Sentiment analysis API — analyze sentiment of text and get a text sentiment score in one call: classifies positive / negative / neutral / mixed polarity with a -1 to +1 sentiment score, plus emotion detection in text (joy, anger, sadness, fear, surprise, disgust, trust, anticipation). Aspect-based sentiment and opinion mining for customer feedback analysis — analyze reviews, support tickets, social posts, chat messages. Via Claude Haiku.

Fetch and parse any XML sitemap or sitemap index file — returns URLs with their priority, change frequency, and last modified date, follows sitemap indexes one level deep (first 3 child sitemaps), and auto-discovers the sitemap from robots.txt or common paths when given a bare domain — so agents can enumerate site content for crawling, indexing, and SEO analysis.

Performs a TLS handshake to inspect the certificate chain, probes supported TLS versions (1.0–1.3), detects weak keys and expiry issues, and returns an overall security grade (A/B/C/F). For just the cert facts fast, see the cheaper /ssl/cert (quick tier).

SSL certificate check for any domain — issuer, subject, SANs, valid from/to, days until expiry, expired/self-signed flags, TLS version, chain length. One TLS handshake, sub-2-second answer. The light, cheap tier under /ssl/analyze (full analysis, grading). No API key.

Calculates IPv4/IPv6 subnet details from CIDR notation — network/broadcast, netmask, wildcard (Cisco ACL) mask, binary/hex masks, usable host range, RFC classification (private/loopback/multicast), supernet, and subnet-split counts. Pass comma-separated CIDRs to detect overlaps and classify each pair (subnet/supernet/partial overlap/disjoint); multi-CIDR responses return {subnets, overlaps}.

Fetch a URL and detect the full technology stack from HTTP response headers, HTML meta tags, cookies, and script patterns — returns CMS, framework, CDN, server, analytics, and security tool detections so agents can profile any web target without a browser.

Text summarizer / summarization API — condense text, Markdown, or a URL into a TL;DR plus key bullet points using Claude Haiku. Accepts raw text or a URL (fetched and extracted), enforces an input cap, and returns a clean structured summary so agents can compress documents and articles in one call.