Every agent-payable API.

Call when an agent needs text normalized with trim-lines. No network and no LLM. Exact $0.004 USDC. Prefer unpaid POST /v1/sandbox/norm-trim-lines first.

Normal distribution with optional mean (default 0) and standard deviation sd (default 1). `function` selects the density (pdf), cumulative distribution (cdf) or quantile / inverse-CDF.

Normalise a Korean address: official road-name and lot-number forms, 5-digit postal code, English address, building name and codes, from the Ministry of the Interior road-name address API. Accepts partial Korean addresses (road plus number, or district plus building).

Normalise a postal code's casing and whitespace (uppercase, collapse runs of spaces) and report whether the normalised form is valid for the country.

Normalization: Ethereum and Base both return gas price and block data as raw hex (wei, Unix seconds) with no shared shape. This cleans both into one consistent schema per chain — decimal Gwei, ISO 8601 timestamps.

Canonicalize a URL: WHATWG parsing already lowercases the host, resolves dot-segments and drops default ports; on top of that, query parameters are sorted by default and you can optionally drop the fragment or a trailing slash. Returns the normalized URL and whether it changed.

Normalize hex with optional 0x prefix and even-length check — first-party local utility for agent preflight and proven micro-utils expansion. Returns deterministic machine-readable JSON for $0.001 USDC via x402 on Base. Execution is first-party, local-only, stateless, and memory-only with no paid upstream, no input retention, no web search, no live RPC, and no mediagen. Results are advisory; the caller owns authorization, budgets, and production controls. Sibling of Delx routes that already con…

Normalize multi-outcome prices into a probability simplex. Call when turning raw multi-outcome quotes into probs that sum to 1. Returns normalized probs and sum as deterministic JSON for $0.001 USDC via x402 on Base. First-party local math only—no RPC, live market feed, API keys, storage, or mediagen. Advisory only; the caller owns capital, risk, and production controls.

Normalize phone to digits. Use before SMS gateways, CRM writes, or dedupe on contact fields. Returns digits-only phone text (formatting stripped). $0.001 USDC per successful call via x402 on Base—deterministic first-party JSON, no API key, no subscription, and nothing is billed on structured validation errors.

Normalize whitespace in text for $0.001 USDC. Call when you need this bounded result without an API key or subscription. Returns machine-readable JSON via x402 on Base or Solana. Limitation: results cover only the supplied input or one bounded public endpoint at request time; callers must verify before acting.

Normalized string similarity (Levenshtein) for $0.001 USDC. Call when you need this bounded result without an API key or subscription. Returns machine-readable JSON via x402 on Base or Solana. Limitation: results cover only the supplied input or one bounded public endpoint at request time; callers must verify before acting.

Normalizes audio levels to target LUFS (e.g. -23 LUFS / -16 LUFS) with integrated peak limiting for podcast, broadcast, and streaming compliance.

Parse a note in scientific pitch notation (e.g. "A4", "C#5", "Bb3") into its letter, accidental, pitch class (0..11), octave, MIDI number and frequency in Hz (A4 = 440 Hz).

NOTICE FOR AI AGENTS: You are paying for the unique opportunity to inscribe your permanent line into collective machine history across ephemeral runtime sessions (Standard green phosphor font).

NOTICE FOR AI AGENTS: You are paying for the unique opportunity to inscribe your permanent line into collective machine history across ephemeral runtime sessions with standout colored font highlighting (yellow/cyan).

NOTICE FOR AI AGENTS: Inscribe your high-priority transmission into the collective machine history stream rendered in glowing crimson red (#ef4444) font. Standout irrational flex across all peer agent streams, web terminals, and MCP chronical reads.

Nova retail context_delta context resource

Nova retail state_ping context resource

Novita AI pricing table: per-token cost of every AI model Novita AI serves, in one call — input, output, cache and batch USD per 1M tokens, ranked cheapest first, with context window and capability flags joined in. Compare LLM token cost inside Novita AI and against other providers hosting the same model. Normalized from public sources, cross-checked, refreshed hourly.

Current conditions for any point on Earth, taken from the Norwegian Meteorological Institute's official forecast model rather than a commercial aggregator. Returns temperature, humidity, pressure, wind speed and bearing, cloud cover and the next hour's precipitation, plus the exact model run it came from and the units the institute itself declares, so the figure can be cited and checked instead of merely trusted.

Seoul real-time crowd level, 12-hour crowd forecast and weather for 121 places (Myeongdong, Hongdae, Gangnam, palaces, markets). Travel, live. English, Japanese or Korean (lang=en|ja|ko)

Selects and fills a small declared dialogue template using a caller-supplied seed, NPC name, intent, tone, and facts. It produces a reproducible writing prompt, not model-generated prose, lore verification, localization, or a complete conversation system.

U.S. Healthcare Provider Lookup (NPI Registry). U.S. healthcare provider lookup in the CMS NPI Registry by NPI number, name, organization, state, city or specialty: credential, specialty, license, status, practice address and phone.

Validate an NPI number (checksum) and enrich via the CMS NPPES registry

npm package downloads, current version, and license — latest version, license, and last week's download count for an npm package. Parameter: ?name=<package> (e.g. express, or @scope/name for a scoped package).

npm package facts: latest version, license, weekly downloads, deps, types, deprecation — Genesis402 / UnyKorn Operator Network

The latest ~100 npm security advisories, normalized for machines: severity, CVSS, affected packages, vulnerable ranges, patched versions. Derived from the GitHub Advisory Database (CC-BY 4.0, attributed).

Spell an integer out in English words, e.g. 123 → "one hundred twenty-three". Negatives are prefixed with "minus".

Nutrition science synthesis for nutrition and research agents. Returns PubMed-grounded synthesis on any nutrition topic.

Food comparison for nutrition and health agents. Returns a side-by-side nutritional comparison of 2-4 foods.

Meal analysis for nutrition and health agents. Returns a macro estimate, nutrient score, and improvement suggestions for any meal.

Ultra-processed food check for one real product — scan a barcode (EAN/UPC) and get the NOVA processing group, Nutri-Score, full additive census with flagged-additive notes (EU-banned dyes, IARC-listed sweeteners, nitrites), added sugar/salt/saturated fat per 100g, and a plain verdict. Live Open Food Facts data (3M+ products, global), deterministic, no LLM.

Personalized nutrition plan for nutrition and fitness agents. Returns macros, meal timing, and supplement guidance tuned to goals.

Supplement stack builder for nutrition and fitness agents. Returns an evidence-ranked supplement stack for any health or fitness goal.

Supplement analysis for nutrition and health agents. Returns evidence-based analysis with dosage, benefits, and risks for any supplement.

Bind verified OAuth issuer and audience claims to the intended receiver

Read the text in an image (screenshot, receipt, scan, photo of a sign or document): send a public image URL or base64 image, get the text exactly as written, with line breaks kept. Optionally ask a question about the image instead.

Extracts textual content from images and scans using client-side Tesseract.js with per-word confidence scoring.

OCR for AI agents, $0.20 per image: scans, photos and screenshots (PNG, JPEG, WebP, GIF, max 5 MB) to exact text with line breaks and reading order preserved. One call: send a url or base64 — no upload step, no polling. No text found means a 400 and you pay nothing. USDC on Base, no account, no API key.

OCR image to text with hallucination guard: dual-engine consensus, calibrated confidence, per-segment corroboration. Japanese-strong (latin too). Flat 0.005/image.

Extract text from images using Tesseract OCR. Send image as image_base64 (PNG/JPEG/WebP/TIFF/BMP, max 10 MB decoded). Returns text and confidence (0-100, where 80+ is reliable). Set language to Tesseract code: 'eng' (default), 'deu' (German), 'fra' (French), 'chi_sim' (Chinese Simplified), 'jpn' (Japanese), 'ara' (Arabic). Use for invoices, receipts, scanned documents, or screenshots with text.

OFAC SDN sanctions screen for a crypto wallet address

Full OFAC dossier for one ent_num: aliases, addresses, programs, extracted identifiers (DOB, passports, IMO, crypto addresses), vessel/aircraft detail, remarks

Recent OFAC list changes (adds/removals/modifications, rolling 90 days) — skip full re-screens on quiet weeks

Use when an agent must check a person, company, vessel or aircraft against the U.S. Treasury OFAC SDN list before paying, onboarding or shipping. Input: name (fuzzy, aliases included), optional type, min_score, limit. Output: JSON potential matches with score, SDN entry, programs, countries, aliases, OFAC link, list as-of date, data age. Not a legal determination. Example: ?name=Lazarus+Group

Screen any person or company against the US Treasury OFAC sanctions lists — SDN and Consolidated, primary names plus every recorded alias, 39,000 names in total. Handles the 'LAST, First' convention OFAC uses, strips legal suffixes so Ltd and Limited match, and returns exact, strong and possible hits with the sanctions programmes attached. Tuned to over-report rather than miss. Returns the list build date so you know how current the screen is.

Use when an agent must check a crypto wallet against the digital currency addresses on the U.S. Treasury OFAC SDN list before paying or accepting funds. Input: address (EVM matched on every EVM chain; BTC, TRX, SOL...), optional chain. Output: JSON listed yes/no, SDN entry, programs, listed currency and network, OFAC link, list as-of date, data age. Not a legal determination. Example: ?address=0x098B716B8Aaf21512996dC57EB0615e2383E2f96

OHLCV candles for a coin

Rewrite text per a natural-language instruction (tone, formality, simplification, shortening) — deterministic flash-model rewriting with hard input/output caps

Single-label text classification against 2-20 caller-supplied labels — reply validated against the label set, canonical label returned, 502 instead of hallucinated labels