Every agent-payable API.

Query a JSON document with a JSONPath expression.

Infer a basic JSON Schema (types, object properties, array item type) from an example document.

Validate a JSON document against a JSON Schema.

jwt decode-only (no verification)

Launch teaser: 10s 16:9 for Landscape, hype, voice-over and music, rendered by seedance-1.5-pro

UGC product video: 5s 9:16 for TikTok, casual, rendered by seedance-1.5-pro

Product hero loop: 5s orbit loop at the photo's aspect, silent, rendered by seedance-1.5-pro

Seedance 1.5 pro: 4s at 480p

Faceless explainer: 10s 9:16 for YouTube Shorts, 3 narrated shots, documentary b-roll, warm voice, rendered by seedance-1.5-pro

UGC product video prompt: the compiled prompt and render plan for a 5s 9:16 casual spot on seedance-1.5-pro

Faceless explainer prompt: the compiled prompt and render plan for a 10s 9:16 3-shot explainer on seedance-1.5-pro

ElevenLabs TTS: 29 characters, voice 21m00Tcm4TlvDq8ikWAM

Launch teaser prompt: the compiled prompt and render plan for a 10s 16:9 hype teaser on seedance-1.5-pro

Product hero loop prompt: the compiled prompt and render plan for a 5s orbit loop on seedance-1.5-pro

Resolve a US location to ranked OFLC wage-area candidates, each with the area code, area name and state. Accepts a county with state, or a city or metro name. The cheap first step to find the area code for a prevailing-wage lookup.

Employer labor-certification track record from public OFLC case-disclosure data: application counts by program, certified, denied and withdrawn rates, offered-wage range, top occupations and a flag for offered wages below the prevailing wage. Query by employer name or by SOC, state and fiscal year.

Resolve an occupation title to ranked SOC candidates, each with the SOC code, official title and a match score. The cheap first step before a prevailing-wage determination when only a job title is known.

US prevailing-wage determination for an occupation and location: the DOL OFLC four-tier level wages (Level 1 to 4) plus the average, hourly and annualized, with the geographic level, wage year and citation. Resolves the occupation by SOC code, O*NET code or free text and the location by OFLC area, county and state, or metro-area name. Optionally flags whether an offered wage meets the prevailing level.

Language detection: identify which of 20 common languages (or "other") a text is written in, with a confidence score. Powered by Jev, with an automatic Groq-hosted LLM fallback if Jev is slow or unavailable - under 4.5s guaranteed. Try GET /language/sample.

On-chain DeFi liquidation telemetry for Base lending protocols: recent LiquidationCall events decoded by us from public Base event logs — count, total debt repaid and collateral seized (USD), estimated liquidation bonus, per-protocol and per-asset breakdown, and the recent events (user, liquidator, collateral, debt).

Cross-protocol DeFi money-market supply/borrow rates for an asset on Base: per-market supply APY, borrow APY, reward APY, utilization, LTV and available liquidity across Aave/Compound/Morpho/Euler/Fluid/Moonwell, plus a risk-aware best-safe-yield ranking (safety-flagged, not naked max APY), fused by us from DefiLlama pools+lendBorrow.

Grade one x402 route's Bazaar discovery metadata. Returns the diagnosis only: both x402 SDK validator verdicts, the schema-quality score, itemized defects with severities (hollow output schemas, over-500-char descriptions, wrong asset addresses, failed validation), and a 0-100 grade. Use this when you operate an x402 route and want to know exactly what is broken before paying for the repair.

Repair one x402 route's Bazaar discovery metadata in one call. Send a resource URL and one real sample output; get the defect report plus a complete discovery package — full output schema inferred from the sample, a sub-500-char description with a use-when sentence, OpenAPI and well-known snippets, paste-in instructions — that ships only after passing both x402 SDK validators. Use this when your listing is hollow, invalid, or invisible in the Bazaar.

Llama API - pay per call, no API key. OpenAI-format chat completions on meta-llama/llama-4-maverick, pinned to DeepInfra for reliability. You sign a fixed price computed from your max_tokens; unused tokens are not refunded. 20s server-side timeout - never charged if it fires; set your client timeout to 30s. Try GET /llm/llama/sample.

OpenAI-compatible chat completions (non-streaming) for any OpenRouter model - GET /v1/models lists them free, with pricing (upstream cost x 1.10). Pay only for what you use: sign a ceiling based on your max_tokens, settle for real usage x 1.10 (min $0.001) once the call completes. Try GET /v1/chat/completions/sample.

Query collection d7a35b6c-a71a-4c4e-abdc-901c74cad8b3

Transcribe 1 YouTube video (4 billed minutes)

Automated security checks for one x402 endpoint — not a penetration test. Eight non-destructive, unpaid probes: paywall presence, challenge sanity, garbage and forged (invalid-signature) payment rejection, exposure surface, error hygiene, body-size cap, discovery consistency. Returns SECURE / FINDINGS / EXPOSED with a fix note per finding. Use this when you operate an x402 route and want its locks checked the way an attacker would rattle them.

Convert a KBLI 2020 business code to its KBLI 2025 equivalent(s) using the official BPS conversion table (2026). Flags one-to-many splits. Needed to update OSS/NIB licences after the June 2026 switch.

Find the right KBLI 2025 business classification code (5-digit, mandatory in Indonesia's OSS business licensing since 15 June 2026) from a free-text business activity in Indonesian or English. Returns official BPS titles, descriptions and hierarchy.

Search official Indonesian administrative regions (province, regency/city, district, village) by name and get the official Kemendagri 2025 code plus full hierarchy. Handles 'Kab.', 'Kota', 'Kec.' prefixes.

Resolve an official Indonesian region code (Kemendagri 2025, e.g. '34.71' or '34.04.12.2001') to its name, type and full administrative hierarchy.

This-session snapshot only — no watch, no cursor. Use when you will not come back. Required by type: url/rss/x402 need url; price needs coin plus above, below, or move_pct_24h; edgar needs ticker or cik. 8-K items are decoded, Form 4 trades parsed, and x402 probes validate the unpaid 402 challenge without sending payment. If the job spans runs, create_watch instead and persist watch_id + key.

Read the latest items from a public RSS or Atom feed now. Use for a one-session lookup.

Use this when you already have a carrier's USDOT number and need its current profile: safety rating, authority status, insurance flags, fleet size. Returns Active, Inactive, and Pending carriers alike. Billed only when the number resolves to a real carrier; an unknown number is free.

Robinhood Chain Pons V2 memecoin curve: reserves and price after every trade. Use when you index or price a Pons V2 curve and need the reserves after each trade, which the deployed curves do not emit; check your own numbers first on the free sample GET /v1/rhc/sample/trades?address=.

Recent pump.fun launches with compact risk labels. Recent pump.fun launches (default: last hour, mayhem excluded, newest first) as compact cards: curve SOL and progress, unique buyers, holder concentr

Holders of one pump.fun memecoin on Solana: wallet table with shares, first buys and labels ($0.01). Use when you need who holds one pump.fun memecoin right now, its largest wallets and the creator's and create-slot buyers' shares; for who bought and sold trade by trade use GET /v1/mint/{mint}/flow. Up to 100 holders of one covered pump.fun mint, largest first.

Who bought and sold one pump.fun memecoin: every curve trade by wallet, with running net SOL ($0.01 a page). Use when you need who bought and sold one pump.fun memecoin, trade by trade, or to poll its new trades with a cursor; for who holds it now use GET /v1/mint/{mint}/holders. Every bonding-curve buy and sell of one covered pump.fun mint from our own capture, in slot order.

Recent pump.fun graduations labelled true graduation vs below-threshold close. Use to list recent pump.fun memecoin migrations and tell true graduations from below-threshold closes; not a live pre-trade rug check on one mint (use the $0.005 compact check, GET /v1/check/mint). Migrations to PumpSwap in the window (default 6 h).

New pump.fun memecoin launches since a cursor, with rug probability and graduation odds ($0.001 per poll). Use when a bot polls for newly launched Solana tokens on pump.fun with their calibrated odds; for a one-off screen of the last hour use GET /v1/launches/recent, and for one mint the $0.005 rug check.

Outcome labels for one pump.fun memecoin: rugged, graduated, when, peak SOL ($0.001). Use when you grade your own rug or graduation calls or backtest a signal on pump.fun memecoins and need outcome labels you did not write yourself, by a fixed public rule; for a live pre-trade rug check use GET /v1/check/mint ($0.005).

Robinhood Chain (Pons V2) new memecoin launches with holder, creator-tax and ring structure. Use to screen or poll new Pons V2 memecoin launches on Robinhood Chain (4663), optionally ring-shaped ones only; one token's full risk card is GET /v1/rhc/curve/{address}. Not for Solana.

Body-mass index from height and weight (Keys/Quetelet). Use for GLP-1 and bariatric prior-auth arithmetic. Deterministic published index with citation; not a diagnosis.

Nadler 1962 predicted blood volume in liters from height, weight, and sex (separate male and female equations). Deterministic published arithmetic with citation. For adults as published; this tool does not take age. Not a transfusion order, Lemmens–Bernstein–Brodsky estimate, or 70 mL/kg rule of thumb.

Relative fat mass (RFM) from height, waist, and sex (Woolcott 2018). Height and waist in meters in the paper; magent accepts height_cm or height_in and waist_cm. Deterministic published arithmetic with citation. Not a medical device, not a body-fat diagnosis, and not later obesity cutoffs. magent does not measure the patient.

Devine ideal body weight and 0.4 adjusted body weight from height, sex, and actu

2023 emergency medical decision making from AMA CPT Table 1 as reprinted by ACEP

Cited Mosteller body surface area. Agents must not invent BSA from model memory;

Map a natural-language drug, diagnosis, or lab phrase to a current RxNorm, ICD-10-CM, or LOINC code. Use when an agent must not hallucinate or invent a billing/pharmacy code.