Query the openFDA Device 510(k) Clearances dataset by search expression, no key, US FDA public data. Returns matching records with structured fields. For AI agents in pharma, device, and safety research.

COVID-19 vaccine doses administered for one country as a daily cumulative timeline (last N days). Keyless disease.sh / OWID. For agents tracking public-health vaccination coverage.

Query the openFDA Drug NDC Directory dataset by search expression, no key, US FDA public data. Returns matching records with structured fields. For AI agents in pharma, device, and safety research.

The list of recipe categories from TheMealDB, no key. Returns category names, thumbnails, and descriptions. For AI agents building food navigation.

Current local time at a lat/lon coordinate via keyless TimeAPI (auto-resolves timezone). Returns ISO date-time, weekday, timezone and DST flag. For agents that only have coordinates, not zone names.

Reverse-geocode lat/lon to country, state, city, locality and postcode via keyless BigDataCloud. Returns ISO codes and admin hierarchy. For agents turning coordinates into human-readable place names.

Cheap, fast "is this a dateable event?" filter for social and web text — one tiny Haiku call returns is_event, confidence, and a one-line reason, so agents can screen every post for free-ish and only pay for full extraction on the ones that pass. Front-end filter to /event-extract; intentionally minimal output for cost/latency discipline.

Generate agent-ready image assets (icons, logos, social graphics, thumbnails, banners) with gpt-image-1. Claude refines the prompt, screens content, adds alt text and a score. Returns image_url as a base64 PNG data URI. Flat $0.25; n=1; ratios 1:1/16:9/9:16.

Turn event fields into a valid RFC 5545 .ics calendar file — handles timed and all-day events, escaping, line folding, and a deterministic UID for idempotent re-import — so agents can publish events that import cleanly into Google, Apple, and Outlook calendars. Pure compute, no LLM.

WHOIS registration lookup — registrar, creation/expiry/updated dates, domain age in days, name servers, DNSSEC, registrant country/org, EPP status codes. All TLDs (.com .net .org .io .dev .ai ccTLDs gTLDs). Per-field error resilience for TLD-specific parsing quirks. No WHOIS library setup or TLD-specific parsing needed. Accepts USDC payments on Base and Solana

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.

Turn unstructured text into structured JSON matching a caller-supplied schema using Claude Haiku — the agent declares the fields and types it wants, and gets back populated JSON with values pulled from the text and coerced to the right types, so agents can structure any prose into the exact shape their pipeline expects.

Parse and normalize a freeform address string using Claude Haiku — splits it into street, city, state/region, postal code, and country, plus a normalized single-line form, so agents can clean and standardize messy address data for shipping, CRM, and verification workflows.

Liu Ren divination, 六壬, Da Liu Ren, 大六壬, Heaven Earth oracle, 12 heavenly generals, 4 lessons 3 transmissions, 四课三传, Chinese astrological divination method. Compute the Da Liu Ren divination chart (Heaven plate, Earth plate, 4 lessons, 3 transmissions) for given datetime.

Geographic distance calculation between two coordinates using haversine formula. Computes great circle distance from latitude longitude pairs. Returns distance in kilometers, miles, and meters. For mapping, navigation, GPS coordinate distance, location based queries, Chinese maps, geo analytics, route planning, proximity search.

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.

Extract structured data from resume/CV text using Claude Haiku — returns name, contact info, skills, work experience, and education as clean JSON arrays so agents can automate applicant screening, candidate databases, and recruiting workflows from raw resume text.

Extract structured data from invoice or receipt text using Claude Haiku — returns vendor, invoice number, dates, line items, subtotal, tax, total, and currency as clean JSON so agents can automate accounts-payable, expense processing, and bookkeeping from raw invoice text.

Chinese hour, shichen, 时辰, 12 traditional Chinese hours, zi chou yin mao chen si wu wei shen you xu hai, 子丑寅卯辰巳午未申酉戌亥, Chinese double hour, 2-hour Chinese time period. Convert any time of day to the corresponding Chinese shichen (one of 12 two-hour periods), including its name, zodiac animal, and elemental association.

Translate up to 2000 words between languages using Claude Haiku — auto-detects source, supports 30+ target languages, preserves formatting, for larger documents and articles. For short snippets use the cheaper /translate/short.