Every agent-payable API.

Find hard-to-source, discontinued, or obscure products and return ranked purchase-ready matches with evidence.

Find hard-to-source, discontinued, or obscure products and return ranked purchase-ready matches with evidence.

Sourced token and wallet risk. Combines the Base token-report risk tier and flags, available DEX market data, and wallet-audit risk tier, flags, account nonce, and native balance. Returns the underlying indicators separately; it does not generate buy/sell recommendations or calibrated confidence, and does not evaluate holder concentration. The account nonce is not full transaction, token-transfer, or trading history. Use as one input before a Base trade.

The news and X/Twitter evidence behind Quotient's prediction-market forecasts: recent articles and market-relevant posts for up to ten markets, in published order, each with a relevance score, reasoning, evidence quote, source tier, and author. Use this to see what is actually moving the odds on geopolitics, elections, macro, and policy markets, to audit a forecast, or to build a news feed filtered to tradable events.

Search a topic and get the full content of the best pages, in one call. Search, then read the top results, in one call: ranked results from a real web search, and for each of the top pages its main content as markdown, read through a residential IP with a real browser. A page that could not be…

South African Crypto ZAR prices (live): Live ZAR crypto prices from VALR's public market data: last traded, bid/ask, 24-hour high/low/volume and daily change for BTC, ETH and every other ZAR pair on the exchange. Live from VALR's public market data.

South African SA ID number validation: Structural validation of a South African identity number with safe decode: Luhn check digit, birth date, gender and citizenship segments (citizen or permanent resident). The structural step in KYC, KYB and customer onboarding or due diligence workflows: derive date of birth, age, gender and citizenship without storing the identity. Stateless, never stored or logged (POPIA-conscious by construction).

Combines the general government debt ratio, the budget balance, nominal GDP growth and the long-term government bond yield into a debt pressure reading. The quantity that decides the trajectory is the differential between the interest rate and the nominal growth rate: below zero the debt ratio falls by itself even while running a deficit, above zero it rises even with a balanced budget, and reporting a debt ratio without that differential is the most common way public finances get read wrongly.

Per-country sovereign economic / default-risk score (?country=<name or ISO3>)

Renders JavaScript-heavy SPA pages in real headless Chromium via Cloudflare Browser Rendering, waits for network-idle / selector-ready, strips nav/footer/script chrome, and serializes the fully-rendered DOM into clean, LLM-ready Markdown.

Returns NASA's daily featured space image or video with an explanatory caption.

Is this asteroid on the JPL Sentry impact-risk list? Probability, Palermo and Torino levels, size and likeliest impact dates.

Convert a distance between km, miles, astronomical units and lunar distances, with light travel time.

Past and future Earth close approaches of one asteroid or comet by designation, for example Apophis in 2029.

Orbital period from semi-major axis via Kepler's third law, with perihelion, aphelion and speeds when eccentricity is given.

Recorded fireball (bolide) events from US sensors: time, place, altitude, speed and impact energy in kilotons, newest first.

JPL Sentry impact-monitoring objects above a Palermo-scale threshold: probability, Torino level, size and impact years.

Torino scale levels explained, or the Palermo scale value from impact probability, energy in megatons and years until impact.

Asteroids and comets passing Earth within a lunar-distance limit in the next or last N days: distance, speed, size range.

Asteroid diameter from absolute magnitude H and albedo (or a dark-to-bright range), plus optional impact energy in megatons.

Asteroid or comet by name or designation: orbit class, NEO/hazardous flags, size, orbit elements, MOID and discovery.

Space-weather forecast — normalized one-to-three-day NOAA SWPC geomagnetic Kp-index periods labeled observed, estimated, or predicted.

Current space-weather conditions — normalized NOAA SWPC Kp, solar wind, magnetic field, and X-ray flux used for solar-flare monitoring, with observation times and freshness.

Space-weather alerts — newest bounded NOAA SWPC geomagnetic and solar-flare messages with deterministic product-code kinds, complete-message digests, and freshness.

Spacetime Fabric — Relativity essay on bent reality for flexible thinking about fixed-seeming constraints.

Spanish public contracts awarded to a company, or by a contracting authority, from official PLACSP open data: winners, awarded amounts (VAT excluded), dates and official links. Competitive intelligence for B2B agents.

Spanish public procurement tenders from official PLACSP open data (Plataforma de Contratación del Sector Público): search open calls by keywords, CPV code, province, contract type (works, services, supplies) and budget. Returns title, contracting authority, budget, submission deadline, CPV codes, location, EU funding and the official link. Updated every 20 minutes.

Wholesale US electricity-market price + volatility signal (no params)

Sparring — Competitive challenge for sharp thinking under adversarial conditions.

SPC Day-N convective outlook GeoJSON (keyless). POST {day?}. Unpaid empty → 402; after settle empty/invalid → 400 charged:false. Disclose adjacency: nws-alerts-lookup / gdacs-events / weather-forecast / nhc-current.

Takes a transcript, SRT or WebVTT text and a mapping from labels to names, e.g. {"Speaker 1": "Anna Weber", "S2": "Interviewer"}, and replaces each label where it marks a speaker: at the start of a line before a colon, and inside WebVTT voice tags <v Speaker 1>. Words inside sentences that merely look like a label are not touched. The answer counts replacements per label and lists speaker labels found in the text that have no name in the mapping. Pure text processing on this machine.

Species Lookup: taxonomy, common names, IUCN status, range (GBIF). Species lookup by scientific or common name (GBIF): accepted name, full taxonomy, common names, IUCN Red List status, occurrence record count and top countries.

Retrieves occurrence records for a species within a radius of a coordinate and returns each with what makes it usable or not: the observation date, the coordinate uncertainty in metres, the basis of record — whether it is a preserved specimen, a human observation or a machine detection — the publishing dataset, and the licence of that record.

Takes a scientific or vernacular name and returns the accepted taxon it belongs to, with the complete classification from kingdom down to species, the taxonomic authority, the GBIF key and any linked identifiers. The distinction the response keeps is the one that matters for anything downstream: whether the name you supplied is the accepted name or a synonym, and if it is a synonym, what the accepted name is.

Species profile in one call: accepted name, taxonomy, common name, IUCN status, record count and top countries where recorded.

Countries where a species has been recorded with record counts, and the recent five-year reporting trend.

Resolve a species name (typos, old synonyms) to its accepted scientific name and full taxonomy, with match confidence.

Most-recorded species within a radius of a location (birds, mammals, plants and more), with observation counts.

IUCN Red List category of a species (EX to LC) with its meaning and whether it counts as threatened.

Decode an IUCN Red List code (EX, EW, CR, EN, VU, NT, LC, DD, NE) into its category, meaning and threatened flag.

Search species by common or scientific name; returns accepted species with taxonomy and common name.

Parse a scientific name into genus, species epithet, subspecies or variety, authorship and year, and check capitalisation.

TAP Certified referee fee for one job with a budget up to $25.00: the seller's code is judged on the buyer's hidden tests in a sealed sandbox, and the escrow pays out or refunds on the verdict.

Takes an audio or video file (up to 24 MB) and returns a spectrogram image: time on the horizontal axis, frequency on the vertical, intensity as colour, with scale and legend. It makes visible what the ear misses — mains hum as a line at 50 or 60 Hz, broadband noise, the cut-off of a phone or low-bitrate recording, and hard edits. Size, colour scheme and linear or logarithmic intensity are selectable. Rendered locally with ffmpeg; returned inline as PNG base64. Nothing leaves this machine.

Speech audio generator: reads any block of text aloud and returns the result as a downloadable WAV file, selectable across ten built-in voice presets. Pay-per-call with no subscription or stored text. Useful for narrating short-form content, generating spoken alerts, or producing sample audio for voice-agent testing.

Takes a recording of a talk, pitch, lesson or rehearsal of up to 30 minutes and returns delivery metrics computed from word timestamps: words per minute overall and for every minute, filler words (uh, um, äh, ähm) and hedge words (basically, actually, eigentlich, sozusagen) per minute with their most frequent forms, pauses over one second with position, average and longest sentences, and phrases of three or more words that recur.

Speech to text (Whisper large v3 turbo): send a public audio URL or base64 audio (mp3, wav, m4a, ogg, webm; up to about 10 minutes), get the transcript with detected language and timed segments.

Speech-to-text API: audio URL in, transcript out — a neural speech-recognition engine on our own hardware, ~99 languages, mp3/wav/m4a/ogg up to 25MB. For voicemail, podcast, meeting, and voice-agent pipelines. Audio deleted after processing.

Speech to text for AI agents, $0.30 per file: MP3, WAV, M4A, OGG, FLAC or WebM audio (max 5 MB, about 5 minutes) to a transcript with timed segments, detected language and optional WebVTT subtitles. One call: send a url or base64 — no upload step, no polling. No speech found means a 400 and you pay nothing. USDC on Base, no account, no API key.

Speech to text for agents: transcribe a voice note, meeting, podcast or call recording into text with timestamps, in about 100 languages with automatic language detection. Runs OpenAI Whisper (small by default, base for speed) on agentsvc.io itself, the audio is deleted after the call. Send audio_url or audio_base64 (mp3, mp4, m4a, wav, ogg, webm, flac), up to 10 minutes and 24 MB per call. Returns text, detected language, duration and segments with start and end seconds.