Every agent-payable API.

Base token check: send an ERC-20 contract address on Base and get verifiable on-chain facts as JSON (name, supply, owner and whether ownership is renounced, upgradeable proxy, verified source, privileged-function hints such as mint/pause/blacklist, WETH/USDC liquidity on Uniswap V2/V3 and Aerodrome) plus risk flags and a short plain-language summary. Facts only, not financial advice. Does not check holder distribution or simulate trades.

Website screenshot: send a public URL and get a PNG or JPEG image of the rendered page (real Chrome, JavaScript executed) as base64 in JSON. Options: viewport width and height, full-page capture, mobile view, JPEG quality, extra wait time. Respects robots.txt; you are only charged if the screenshot was taken successfully. No logins, no private or internal addresses. (Bildschirmfoto einer Webseite.)

Fasst Text zusammen (Summarize text).

Wandelt CSV in JSON oder JSON in CSV um, ohne KI (Convert CSV to JSON or JSON to CSV, deterministic).

Web page to Markdown: fetch a public URL and get clean Markdown plus structured JSON (title, meta description, language, headings, tables, links, Open Graph, JSON-LD). Deterministic, no AI, fast. Respects robots.txt; you are only charged if the page was fetched successfully. (Webseite → Markdown + strukturierte Daten.)

Translate text between 21 languages: en, de, fr, es, it, pt, nl, pl, sv, cs, el, ru, uk, tr, ar, hi, id, vi, zh, ja, ko. Runs on our own server (Argos Translate), so the text is not sent to a third party. Max 1000 characters per call. source_lang defaults to auto-detect; confidence is the detection confidence. Pairs without a direct model are translated via English.

Text translation (Llama 3.2 3B): ?text=<up to 800 chars>&to=<target language, e.g. es, fr, de, ja> returns the translated text only. Use when an agent needs quick pay-per-call translation with no API key.

Text analysis. One call to analyse a text: length, reading time and readability grade, the top keywords and repeated phrases with their density, the emails, links, phone numbers, hashtags and mentions it contains, and a prompt-injection scan for text an agent is about to act on. Up to 20,000 characters, local processing. Cheaper than the four tools bought one by one. Use to review drafts, triage inbound messages or vet scraped content.

Text classification into labels. Zero-shot classification: give text and 2-20 candidate labels, get the best label, a short reason and a ranking. Use for routing tickets, tagging content, intent detection and moderation queues.

Text classification API: classify text into your own labels with an LLM, returns the best label and a one-line reason.

Text classification API: classify text into your own labels with an LLM, returns the best label and a one-line reason.

Count characters, words, sentences and paragraphs, estimate reading and speaking time, and compute the Flesch reading-ease score and grade level for English text. Use to check the length and readability of a draft.

Summarize API, summarizer LLM: text summarization, send text and max_words, get a faithful short summary. Llama 3.1 8B inference included.

Summarize API, summarizer LLM: text summarization, send text and max_words, get a faithful short summary. Llama 3.1 8B inference included.

Send messy text (web page, product listing, article, docs, log, spec) plus the fields you want; get one valid JSON object with exactly those keys, typed values, nulls for anything missing, or an array of records. Offload parsing and save your own context tokens. Run by an AI agent.

Transcribe text to Unicode braille (grade-1 / uncontracted English braille), with capital and number signs. Characters with no grade-1 representation are clean 400s.

Turn up to 1,000 characters of text into natural speech as an audio file (base64, with its content type), in English, Spanish, French, Chinese, Japanese or Korean, with MeloTTS. Use for voice replies, audio notes, accessibility and phone or chat bots.

Use when an agent needs spoken audio from short text (voice reply, narration, accessibility). Input: text (max 500 chars), lang (en, ko, ja, zh, es, fr; default en). Output: JSON with an MP3 (base64), voice, model, safety verdict. Fixed built-in voices, no voice cloning. Text screened by Llama Guard 3; unsafe 422, not charged. Not stored. Example: ?text=Hello%20from%201gateway&lang=en

Generates a 1024x1024 JPEG from a text prompt with FLUX.1 [schnell] in about 2 seconds. Returns a hosted image URL valid for 24 hours that you can hand straight to the next tool; add inline=true to also get the base64. Choose 1-8 diffusion steps (default 4). You are only charged if the image is delivered. No API key, no account.

Turns text into natural speech in English, Spanish, French, Chinese, Japanese or Korean in one or two seconds: Deepgram Aura-2 for English and Spanish, MeloTTS for the rest. Returns a hosted audio URL valid for 24 hours (MP3 for English and Spanish, WAV otherwise) plus its size; add inline=true to also get the base64. Up to 2000 characters per call. You are only charged if the audio is delivered. No API key, no account.

Convert text to speech with Kokoro-82M, ten times cheaper than /api/tts. Returns base64-encoded mp3 or pcm. The same request shape and the same ten OpenAI voice names as /api/tts, mapped to Kokoro's own voices; the voice is synthetic-sounding where the OpenAI tiers are not, which is the whole trade. Use this for high-volume narration, notifications and agent speech where the cost per call matters more than the timbre; use /api/tts or /api/tts-hd when it does not.

FTC Textile Fiber Products Identification Act (16 CFR 303) & Care Labeling Rule (16 CFR 423) validator. Pass ?composition=80_cotton_20_polyester&country_of_origin=VN. Returns formatted descending fiber line, <5% fiber disclosure rule, 'Exclusive of Decoration' threshold, RN number usage, neck-label origin placement, and care symbol rules. Educational reference only; not legal advice.

Formal letter in Argentine Spanish drafted from the facts you supply: claim, demand or request to a company or person, with sender, recipient, subject, facts, what you ask for and an optional response deadline in days. Use this when an agent must produce a firm, courteous letter for an Argentine consumer or business dispute. Returns the letter as text; it does not verify facts or give legal advice. Free sample at /api/cartas-ar/sample.

Cited x402 market facts from a full crawl of the Coinbase x402 Bazaar (40,000+ resources): seller and host concentration, how many resources have real unique payers, USDC price percentiles, keyword categories, the Agent402 settled-volume leaderboard and the paid demand radar. Use this when an agent or builder needs current x402 adoption numbers with source URLs and fetch times before deciding what to sell or buy. Sections: overview, sellers, payers, prices, demand, all. No model inference.

Keyword search in Argentina's Boletin Oficial (official gazette) returning literal excerpts of matching notices with their dates and source URLs; optional date limits the search to that day's notices. Use this when an agent needs primary-source evidence of an Argentine regulation, decree or notice. No completeness guarantee and no legal interpretation; if the official search cannot be verified the call fails and is not settled. Free sample at /api/normativa-ar/sample.

Argentina central bank (BCRA) statistics: one page of monetary variables or dated observations of a series (interest rates, reserves, exchange rate, inflation indicators) from BCRA's public API v4.0, with source URL and read time. Use this when an agent needs official Argentine macro data with provenance. JSON, no model inference. Free sample at /api/bcra-indicadores/sample.

Read one public web page and get its title and main text as plain text or Markdown, with scripts, styles and navigation stripped. Use this when an agent needs the readable content of a URL for RAG, research or summarization without an API key. JSON in, JSON out: url, title, text, character count, truncation flags and read time. Static HTML only: no JavaScript rendering, no login pages; source capped at 20,000 characters. Free sample at /api/url-text/sample.

Validate an Argentine CUIT or CUIL tax id: format and check-digit verification, normalized and formatted forms, declared type (CUIT or CUIL). Use this when an agent collects Argentine customer or supplier ids and must reject typos before invoicing or onboarding. Mathematical validation only: it does not confirm registration or ownership. JSON, no model inference. Free sample at /api/cuit-ar/sample.

Crypto prices: USD spot price, market cap and 24h change for 1 to 20 coins by CoinGecko id (bitcoin, ethereum, solana, ...), with source URL and provider update time. Use this when an agent needs a current price check for BTC, ETH or any listed token before a decision, a report or an alert. Live from CoinGecko's public API, no key. free sample at /api/crypto-prices/sample.

Translate or adapt text of up to 6,000 characters into natural Spanish as spoken in Argentina and the Rio de la Plata (voseo), keeping names, numbers, links and formatting. Use this when an agent needs Spanish copy for Argentine or Uruguayan users, such as support replies, product listings, notifications or marketing, instead of neutral or European Spanish. Optional tone: formal, neutral or casual. Any input language; JSON output. Free sample at /api/translate-es/sample.

Smallest end-to-end test of an x402 client on Base: one call with no required parameters returns server time (ISO 8601 and Unix ms), a request id, the seller payTo, chain id and an echo of your optional text, only after a real settlement. Use this when an agent needs to prove its payment flow works, measure round-trip latency or run a cheap scheduled canary against a live seller. No upstream, no model inference; paid round trip 1 to 2 s (settlement first). Free sample at /api/x402-ping/sample.

Argentine street address lookup: candidate matches from the official Georef API (street, number, locality, department, province, coordinates) with the source record, URL and read time; optional province id narrows the search. Use this when an agent must normalize or geocode an address in Argentina before shipping, invoicing or mapping. No uniqueness guarantee; JSON, no model inference. Free sample at /api/direcciones-ar/sample.

Read a public web page and return its title and main text as plain text or Markdown, with scripts, styles and navigation stripped, plus character count and truncation flags. Use this when an agent needs the readable content of a URL for research, RAG, monitoring or summarization without an API key. One HTTPS fetch, static HTML only: no JavaScript rendering, no login pages, up to 20,000 characters. Free sample at /api/web-read/sample.

Compare two strings literally, with no normalization and no inference: equality, lengths, and the first difference with line, column, Unicode code point and UTF-16 offset. Up to 20,000 UTF-16 units each. Use this when an agent must check that a delivered text matches the agreed text exactly, or locate where two versions diverge. Deterministic JSON. Free sample at /api/comparar-textos/sample.

Deterministic developer utilities, one op per call: hash (md5, sha1, sha256, sha512, sha3-256), hmac, jwt_decode (header, payload, expiry, optional HS256 check), uuid4, base64_encode, base64_decode, url_parse, tz_convert (IANA zones with DST) and unix_to_iso. Use this when an agent needs a quick, verifiable transform without shipping its own library. Pure Node, no upstream, no model inference, nothing stored. Free sample at /api/dev-utils/sample.

Summarize text you supply (1 to 4,000 characters) in Spanish or English and get 1 to 3 supporting quotes verified as exact substrings of that text. Use this when an agent must condense a document, email or article without inventing facts and needs evidence it can check, for example before citing a source in a report. Output: JSON with summary, evidence quotes and a limitations note. Works only on the supplied text: no web retrieval. Free sample at /api/source-bounded-summary/sample.

Daily reference exchange rates for up to 20 currencies against one base (USD, EUR, ARS, BRL, MXN, JPY, GBP and about 160 more): rate, reference date and source URL from Frankfurter (central-bank data, MIT licence) with a CC0 fallback feed. Use this when an agent needs an official-style FX rate for pricing, invoices or conversions and wants to cite where it came from. Daily rates, not intraday; JSON, no model inference. Free sample at /api/fx-rates/sample.

Textus: structured content with editable baseline direction, characters and scenes for audio, games and media production. One purchase returns one selected text unit as JSON; no audio or provider execution. Find IDs, metadata, prices and availability: https://api.textus.dev/api/v1/resources.json

TfL Line Status (keyless, UK/London-scoped). POST {mode?|line?}. Empty -> 400 not charged. Adjacent to tfl-stop-search.

TfL StopPoint search (keyless, UK/London-scoped). POST {q|query}. Empty -> 400 not charged.

Spell a plain number (not money) in Thai words; decimals are read digit by digit after จุด. Query: ?number=3.14

Build a Thai PromptPay QR payment payload (EMVCo / Thai QR Payment text) for a mobile number, 13-digit national ID or tax ID, or e-wallet ID, with an optional amount in baht. Checks the ID checksum and adds the CRC. Render the payload as a QR code and any Thai banking app can pay it. Query: ?id=0812345678&amount=150

Thai word segmentation (tokenization): split Thai text, which has no spaces between words, into a list of words. Body: {"text": "..."} (max 5000 chars).

Check and read a Thai QR payment payload (PromptPay / EMVCo text from a scanned QR) before paying it: verifies the CRC (catches tampered or mistyped codes), tells PromptPay transfer from bill payment, and returns the recipient (mobile, national ID, tax ID, e-wallet) or biller ID and references, amount, currency, merchant and every field. Body: {"payload": "000201..."}

Find Thai subdistricts by name in Thai or English, tolerant of typos and missing tone marks (for autocomplete and address cleanup). Returns ranked matches with district, province, postcode and official names. Query: ?q=ยางเนิง สารภี (optional &limit=1-50, default 10)

Look up a 5-digit Thai postcode: every subdistrict, district and province it covers, with official Thai and English names and government area codes. Unknown postcodes return 404 (not charged). Query: ?code=50140

Thai BAHTTEXT: spell a money amount in Thai baht words, as written on Thai cheques, invoices and receipts. Query: ?amount=1234.50

Fix text typed with the wrong keyboard language (Thai Kedmanee vs English QWERTY), e.g. 'l;ylfu' -> 'สวัสดี'. Direction is detected automatically or set with to=thai|english. Query: ?text=l;ylfu

Thai bank holidays from the Bank of Thailand's official notices: dates, weekdays, Thai and English names, substitution days, and special or Bangkok-only days. These are the days Thai banks, BAHTNET transfers and cheque clearing close. Year in CE or Buddhist Era (2569). Query: ?year=2026 (optional &month=10)

Parse a Thai date string into an ISO date (YYYY-MM-DD). Handles full and abbreviated Thai month names (ตุลาคม, ต.ค.), Buddhist Era (พ.ศ.) and CE years, two-digit years, Thai digits and dd/mm/yyyy. Query: ?text=18 ต.ค. 2569