Every agent-payable API.

Patent search. Send keywords, a technology description or an assignee name; returns up to 10 Google Patents results with title, publication number, priority, filing, grant and publication dates, inventor, assignee, snippet and PDF link. Use for prior-art scans and competitor patent checks. Not legal advice. Typical response about 1 s. Failed calls are not charged.

Sanctions screening against the US Treasury OFAC SDN and Consolidated lists. Send a person, company or vessel name (fuzzy match on names and aliases, with scores) or a crypto wallet address (exact match against addresses OFAC lists). Returns matching entries with program, list, score and list date. Use as a first screen before a payment or onboarding. A screening aid, not a compliance determination. Failed calls are not charged.

On-page SEO audit of one URL: redirects, title and description lengths, canonical, robots meta and robots.txt for Googlebot, GPTBot and ClaudeBot, hreflang, headings, image alt, links, Open Graph, JSON-LD, sitemap, security headers with a grade, and a list of issues. Use to check a page before or after publishing. Reads the first 300 KB; no JavaScript rendering. Social networks are refused. Typical response 1 to 3 s. Failed calls are not charged.

Company legal-entity lookup from the global LEI system (GLEIF). Send a company name or a 20-character LEI; returns legal name, LEI, status, jurisdiction, legal form, registration number, registered and headquarters addresses, and the first record's direct and ultimate parents. Use for know-your-business checks, invoices and group-structure questions. Companies only. Typical response 1 to 2 s. Failed calls are not charged.

Email authentication check for a domain. Returns the SPF record with its DNS lookup count and all qualifier, the DMARC policy and report addresses, MX hosts, MTA-STS and BIMI records, DKIM keys found on common selectors, a grade from A to F and a list of issues. Use to diagnose deliverability or spoofing risk. DKIM is checked on common selectors only. Typical response under 1 s. Failed calls are not charged.

Markdown to PDF. Send Markdown (headings, lists, tables, links, bold, italic); returns an A4 PDF as base64 in JSON. Use to hand a person a printable report or invoice-style page. Images and raw HTML are not rendered. Up to 50,000 characters. Typical response under 1 s. Failed calls are not charged.

Scholarly paper search. Send a topic or title, or one DOI; returns up to 20 published works with title, authors, year, journal or venue, type, DOI link and citation count from Crossref. Use to find and cite papers. Metadata only, no abstracts or full text. Typical response 1 to 2 s. Failed calls are not charged.

Email address check without sending mail. Returns syntax validity, the normalised address, whether the domain accepts mail (MX, null MX or address fallback), and flags for disposable, role (info@, support@) and free webmail addresses, with a verdict. Use to validate an address someone gave you. Does not confirm the mailbox exists. Typical response under 1 s. Failed calls are not charged.

Web page to PDF. Send a public URL; returns the page's main content as a clean A4 PDF (base64 in JSON), text and tables only, without navigation or ads. Use to archive or share an article. No JavaScript rendering, images or pages behind logins. Typical response under 3 s. Failed calls are not charged.

Batch Google web search. Send 1 to 10 queries in one call; returns up to 10 ranked results per query (title, URL, snippet, date) in the order sent, for one flat price. Cheaper than /v1/web-search from 3 queries; for 1 or 2 use /v1/web-search. Typical response 2 to 4 s. Failed calls are not charged.

Brief to PDF. Send a short brief; returns a 400 to 900 word document written from it, laid out as an A4 PDF (base64 in JSON) plus the Markdown text. Use for a one-page explainer, memo or checklist. It uses only the facts in the brief and general knowledge; no web search. Typical response 5 to 15 s. Failed calls are not charged.

Web search. Send a query; returns up to 20 ranked Google web results with title, URL, snippet and date where known. Use when an agent needs links to read or to check what exists on the web. Not for reading page content (use /v1/fetch-page) or for a written answer (use /v1/research-answer). Typical response 1 to 2 s. Failed calls are not charged.

Cited research answer. Send one question; returns a 120 to 300 word answer with numbered [n] citations and the source URLs read, each with the time it was read. Searches the web, or reads only the urls you pass. Suited to an agent that needs a sourced answer it can show a person. Not for raw result lists or pages behind logins. Typical response 5 to 12 s. Failed calls are not charged.

Sentiment: a composite market-mood read for one symbol from our own pipeline: model lean, price momentum, and news tone (when our news feed has items). Each component is shown with its inputs. Experimental. Not financial advice.

Track Record: every stored Kronos signal and its scored outcome, misses included (the signal+outcome dataset). Pay per call via x402. Not financial advice.

News: recent headlines for one symbol from our own news pipeline, each with a tone score, plus the average tone. Empty results are reported as empty (never charged), not as neutral. Experimental. Not financial advice.

On-demand Kronos Forecast: any crypto pair (e.g. PEPE-USD) or US stock ticker outside the scheduled list. We check that candles exist (else 404, not charged), then run Kronos on our forecast worker. Fresh stored result: 200 with the fact list. Otherwise 202 with job_id and a free status_url to poll (typically ~3 minutes), plus an optional signed webhook. Frequently requested symbols are added to the scheduled list. Experimental, not calibrated. Not financial advice.

Research brief for one crypto pair in a fixed JSON schema (brief-1.0): Kronos lean and 80% range, 48h news tone, realized volatility, 1-day VaR and expected shortfall, max drawdown, correlation to BTC, a news/forecast conflict flag and a short guarded rationale. Works for scheduled and on-demand pairs. Errors are never charged. Informational, not financial advice.

Signal Blend: one merged multi-source fact list per symbol: Kronos signal + market data (momentum, volatility range, invalidation check) with a stance and plain-English reasons, plus a prediction_markets block: nearest-dated Polymarket "above $X" market prices next to an experimental model view of our volatility-based range (not odds). News/sentiment inputs rolling out. Experimental. Not financial advice.

Kronos Forecast: the Kronos candlestick model signal for one symbol and interval as a standard JSON fact list (direction, confidence bucket, volatility-based range, invalidation level, per-step percentiles). Live: BTC-USD, ETH-USD 1h; stocks, forex and commodities rolling out. Experimental, not calibrated. Not financial advice.

Kronos Forecast: the Kronos candlestick model signal for one symbol and interval as a standard JSON fact list (direction, confidence bucket, volatility-based range, invalidation level, per-step percentiles). Live: BTC-USD, ETH-USD 1h; stocks, forex and commodities rolling out. Experimental, not calibrated. Not financial advice. Timeframe: 1h.

Kronos Forecast: the Kronos candlestick model signal for one symbol and interval as a standard JSON fact list (direction, confidence bucket, volatility-based range, invalidation level, per-step percentiles). Live: BTC-USD, ETH-USD 1h; stocks, forex and commodities rolling out. Experimental, not calibrated. Not financial advice. Timeframe: 15m.

Kronos Forecast: the Kronos candlestick model signal for one symbol and interval as a standard JSON fact list (direction, confidence bucket, volatility-based range, invalidation level, per-step percentiles). Live: BTC-USD, ETH-USD 1h; stocks, forex and commodities rolling out. Experimental, not calibrated. Not financial advice. Timeframe: 4h.

Stock Forecast: next-session and 5-day forecast for US stocks/ETFs (SPY, QQQ) from our own candle store and a seeded bootstrap baseline model: direction, probability-of-up share of sampled paths, 80% range, invalidation level, per-step percentiles. Experimental, not calibrated. Not financial advice.

Kronos Forecast: the Kronos candlestick model signal for one symbol and interval as a standard JSON fact list (direction, confidence bucket, volatility-based range, invalidation level, per-step percentiles). Live: BTC-USD, ETH-USD 1h; stocks, forex and commodities rolling out. Experimental, not calibrated. Not financial advice. Timeframe: 1d.

Quantum Entanglement — Instant correlation theory for understanding connection across distance without transmission.

Post-quantum TLS capability check for a public hostname on port 443. Four live handshakes test X25519MLKEM768, pure ML-KEM and classical TLS; includes HSTS, certificate trust/expiry, CAA and x402 discovery. Returns a heuristic score out of 90, probe findings and remediation. Measures one address at one moment, not all clients, origin connections, wallet safety or compliance.

Quantum Shots — Quick philosophy on superposition and uncertainty for embracing ambiguity in decision-making.

Bazaar Scout: searches the Coinbase Bazaar for a capability, live-probes the top candidates (still returning HTTP 402? how fast?), and returns a ranked shortlist with a best-value pick — a vetted result set, not a raw listing dump.

South Korea's exports from Korea Customs Service statistics: 10-day provisional totals, change vs prior month and year, major items, HS codes and countries, with revisions tracked. Korean or English question; observed values only.

Korean apartment sale prices from the MOLIT real-transaction register: trades, median price and price per m2 by district, month and complex, from a Korean or English question. Observed registered trades only.

Korean listed-company disclosures from OpenDART as change tracking: filings, corrections linked to their originals with before and after values, and a point-in-time view. Ask about a company in Korean or English.

Query or append signed evidence-backed agent limitation records with correction and dispute handling.

Live betting lines for NFL, NCAAF, MLB, NBA, NCAAB and NHL: spread, total, both moneylines and per-book detail for every game on the board.

Evaluate a JMESPath expression against a JSON value and return the selected/projected result. A malformed expression is rejected before payment.

Query recent x402 payment history for seller

Two directions over query strings. action='parse' decodes a query string (with or without a leading '?') into an object, collapsing repeated keys into arrays. action='build' encodes a params object into a query string, expanding array values into repeated keys; set sort=true to order keys alphabetically.

Selects objective framing, complication, and reward language from declared templates using a caller seed. It returns a bounded quest outline, not model-authored narrative, encounter balancing, unique lore, scripting, or playable content.

Quest pacing — Record quality audit + String normalisation + Numeric interval filter: Record quality audit + String normalisation + Numeric interval filter for supplied quest pacing records (duration_minutes, objective_count). Up to 200 rows; 3 independent reports using shared local analytical engines. No live lookup, prediction, professional assessment or external action. 0.01 USDC includes 3 supplied-data reports for up to 200 rows.

Create an open-question register ordered by source timestamps with stable tie handling. Reuses exactly one existing qualified meeting-notes request. Supplied source goes to the existing Groq model in the USA; existing processor disclosure and cost/margin retained. Notes quotes/owners/deadlines are verified by the unchanged motor first. Extra rules are deterministic; no semantic deadline resolution or specialist advice.

Quick KYA Trust Score for any AI agent wallet. Returns score (0-100), tier, and sanctions status. Paid via x402 USDC.

Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.

Quick research: ask any question, get a concise sourced answer with key points, sources, a confidence rating, and anything that could not be verified.

Before an AI agent trusts or pays a public API, inspect its public machine-readable evidence and x402 readiness. Submit a public HTTPS domain to check its agent card, OpenAPI, robots policy, and settlement-aware x402 signals, or submit a Base address for public onchain evidence. Returns a timestamped JSON report; not a security or compliance audit.

Quick risk score (0-100) for entity name + country. Lightweight check without full data source scan.

LaunchCheck full report for one public URL: status code, HTTPS/redirects, title/description, Open Graph/Twitter card, robots.txt/sitemap/noindex, plus up to 50 links checked for breakage, og:image load check, desktop 1280x800 and mobile 390x844 JPEG screenshots, edge TTFB and real-browser load time, image alt text, heading outline, mobile overflow, and a P1-P3 prioritized fix list. Read-only. Unreachable sites are not charged.

Drop-in OpenAI Embeddings endpoint: POST {input: string | string[], model, encoding_format: float|base64, dimensions} and get {object: "list", data: [{embedding, index}], model, usage}. Models (Cloudflare Workers AI): bge-m3 (1024-d, multilingual (100+ languages), 8192-token context); bge-large-en-v1.5 (1024-d, English); bge-base-en-v1.5 (768-d, English); bge-small-en-v1.5 (384-d, English, fastest); embeddinggemma-300m (768-d, multilingual (Google EmbeddingGemma)). Any other model name (e.g....

Live crypto prices for up to 25 coins per call: pass tickers in `symbols` (BTC,ETH,SOL,AERO,...; common tickers built in, others resolved by CoinGecko search to the largest coin with that ticker), CoinGecko `ids`, or one token `address` + `chain` (base default; ethereum, arbitrum, optimism, polygon, bsc, avalanche, solana). Returns price, market cap, 24h volume and 24h % change in each `vs` currency (usd default; up to 5, e.g. usd,eur,btc) plus last-updated time. Data: CoinGecko public API,...

Returns the caller's public IP address (IPv4/IPv6) as seen at the Cloudflare edge, with approximate geolocation (country, EU flag, continent, region, city, postal code, latitude/longitude, timezone), network (ASN and AS organization), the Cloudflare colo that served the request, HTTP protocol and TLS version. Useful for an agent to check its own egress IP/region, confirm a proxy or VPN, or smoke-test an x402 wallet with a cheap paid call. No params. Errors are never charged.

Look up one transaction on Base mainnet by hash: status (success, failed or pending), block, timestamp, confirmations, from/to, value, method id, gas used, effective gas price, fee split into L2 execution and L1 data fee (ETH and USD), contract created, and decoded ERC-20 Transfer events (token, symbol, from, to, amount; up to 20). Useful to confirm a payment landed. Read live from public Base RPC. All params optional: defaults to a confirmed USDC x402 payment. Unknown hash = 404, invalid...