Use when an agent needs award flight search. Returns Validate and normalize an award-flight search (origins, destinations, date window, cabin, passengers) into a stable machine-readable request and response shape, without claiming inventory Oblique does not hold. $0.02.

Search X/Twitter for any topic, ticker, hashtag or account and get the 20 newest matching tweets as clean JSON: text, author, followers, likes, retweets, views, URL. Operators: from:user, "exact phrase", #hashtag, min_faves:, lang:, since:/until:. No API key or login. Empty result is free; next.older pages deeper. ?query=<advanced search>. AI summary instead: /x/digest $0.05.

Multi-chain JSON-RPC passthrough fronted by BlockRun, powered by Tatum's gateway across 40 chains (Ethereum, Base, Solana, Polygon, BSC, Arbitrum, Optimism, Avalanche, Bitcoin, Sui, and more). One endpoint, every chain, pay-per-call in USDC, no API key. $0.002 per call (or per element of a JSON-RPC batch). Network: Base.

Get a complete smart wallet profile with all metrics

A QR code for a text of up to 300 characters (a URL, Wi-Fi login or contact card), generated locally. format=svg returns the image itself as image/svg+xml; format=json returns the version, the module count, the SVG and a data URI. Error correction L, M, Q or H (default M); size from 128 to 1024 pixels (default 512).

US federal bills from Congress.gov (Library of Congress). Keyword search (q) runs over the 250 most recently updated bills of a Congress, since the API has no full-text search; each match gets its sponsor, status and latest action. A bill number (bill=hr1234-119) returns its cosponsor count, committees and up to 30 actions. Public domain.

Text-to-speech as base64 audio. Default: MeloTTS WAV, up to 2,000 chars, in English, Spanish, French, Chinese, Japanese or Korean, $0.002. quality "high": Deepgram Aura-2 natural English voices as MP3, up to 500 chars, $0.02.

Converts text, JSON or JSONL to cleaned JSONL using fixed rules. Removes empty, short and duplicate rows; can repair some encoding issues. No AI or CSV parsing.

Official rate and macro series in one call, by name: fed_funds, us_cpi, us_core_cpi, us_unemployment, us_10y, us_2y, us_mortgage_30y, us_gdp, wti_oil, brent_oil, henry_hub_gas, us_house_price_index, ecb_deposit_rate, ecb_main_refi_rate and euro_area_hicp. Latest value, change vs previous and vs a year earlier, and observations. Up to 6 series. FRED (US public domain), the ECB Data Portal and Eurostat.

The language of a text with franc-min: ISO 639-3 and ISO 639-1 codes, the English name, confidence from 0 to 1, the script (Latin, Cyrillic, Arabic...) and the three next most likely languages. Send texts= (a JSON array of up to 20 strings) for a batch. Under 20 characters the answer is und with a note. 61 languages.

Security headers of a URL's final response: Strict-Transport-Security, Content-Security-Policy, X-Frame-Options (or CSP frame-ancestors), X-Content-Type-Options, Referrer-Policy, Permissions-Policy, Cross-Origin-Opener-Policy and Cross-Origin-Resource-Policy, each with present, value, ok and advice. Also cookies missing Secure, HttpOnly or SameSite (names only), version leaks in Server or X-Powered-By, and a grade from A to F.

Mail and DNS hygiene of a domain over DNS over HTTPS: A, AAAA, MX, NS, TXT and CAA records; SPF parsed (mechanisms, the all qualifier, a lookup estimate, a warning above 10 lookups); the DMARC policy; DKIM keys under common selectors; MTA-STS, TLS-RPT and BIMI; an issues list and a mail grade from A to F.

Get OHLCV candlestick data for a Binance trading pair

A public GitHub repository: stars, forks, watchers, open issues and pull requests, license, default branch, created and pushed dates, topics, languages with shares, latest release, commits in the last four weeks and the top five contributors. Up to six GitHub requests per call. Commit statistics are null while GitHub computes them. Source: GitHub REST API.

Speech to text from a media link: TikTok, X, SoundCloud, Facebook, Dailymotion, podcasts, Drive or Dropbox links, direct audio or video files. Text, timestamped segments, language, duration; speaker labels on request. Price from maxMinutes (default 5, up to 120): direct file up to 25 MB $0.001 + $0.0006/min, other links $0.002 + $0.0009/min, speakers=1 $0.01/min. Longer media is refused unpaid. YouTube returns captions. No speech is a 404, not charged.

MCP server security scan: probe any MCP endpoint's initialize handshake and tools/list and report whether it requires authentication, which protocol version it speaks, how many tools it exposes and which are not marked read-only. Use it before connecting an agent to an unknown MCP server. Input: url of the MCP endpoint.

Structured facts from a web page / scrape to JSON: name the fields you need (pricing, plans, contact, product names, anything) and get exactly those keys back as JSON from the live page rendered in a real browser, null where the page does not say. Use it for price monitoring, lead data and catalog extraction. Input: url, fields[].

Anomaly detection on a time series: score recent periods against history with BigQuery AI.DETECT_ANOMALIES (TimesFM). Give one table and its latest periods are scored against its own history, or a history and a target table. Returns every checked row with bounds, anomaly flag and probability, plus the anomaly count. Input: history_table, target_table, timestamp_col, data_col; optional target_last, threshold, id_cols.

Product availability and price check: is it in stock and buyable right now, at what price, in which options (sizes, colours, dates, rooms), which option matches the variant you name, quantity and ship-to eligibility where the page states them, with evidence and a checked_at stamp. Reads any product or booking page (schema.org, Open Graph, Shopify JSON; a browser only when needed). Input: url; optional variant, quantity, ship_to.

Same KOL confluence feed as kol_signals_live with every row at least 45 minutes old — the evaluation tier