other

List Wirecutter review URLs from the public Wirecutter review sitemaps. Defaults to recommendation-like review pages.

One-call executive brief on a company: aggregates enrichment + news + website + risk, then an LLM distills it into overview, products, developments, risks, opportunities.

Recent Google Maps reviews for a place: author, text, rating, date, owner response, plus the place summary. Give a place_id or a query.

Borrow-Curve Stress Test analyses only the evidence supplied by the caller. It does not claim to query a chain, identify a legal status or replace an independent audit. Missing signals lower confidence and are listed explicitly; every classification includes the exact thresholds used.

Time-series forecasting: forecast any BigQuery table with Google's pretrained TimesFM model (AI.FORECAST), nothing to train. Point it at the table, timestamp column and value column and get forecast rows with bounds for the horizon you set, per series with id_cols. Use it for sales, traffic, demand or metric forecasts. Input: table, timestamp_col, data_col; optional horizon, id_cols.

A US-listed company's latest SEC filings by ticker or CIK - 10-K, 10-Q, 8-K with its item codes, insider Form 4, proxy statements - each with its date and a direct link to the document on sec.gov, plus the company's CIK, exchanges and industry. Filter by form type. Pay-per-call via x402. An empty body is answered for the published example ticker (AAPL); send {"ticker":"…"} for any other company.

Who holds an ERC-20: the top 10 holders with their share of supply and whether each is a contract, locked or a burn address, the LP holders and how much LP is locked, the creator's and owner's share, holder count, and concentration with burned/locked supply excluded. Base, Ethereum and five more chains. Send {} for USDC on Base. Pay-per-call via x402. An empty body is answered for USDC on Base (the x402 settlement asset); send {"token":"0x…"} for any other token.

Speech to text / audio transcription: transcribe up to 60 seconds or 10 MB of audio with Google Cloud Speech-to-Text and get the transcript with its confidence and detected language. Use it for voice notes, call snippets and clips. Input: audio_base64; optional language_code. Longer audio is refused before payment.

Text to speech (TTS): convert text to natural spoken MP3 audio with Google Cloud Text-to-Speech, returned as base64. Use it for voice replies, narration, audio versions of text and accessibility. Input: text; optional voice name.

Question answering over your own text: ask a question about material you supply and get an answer grounded only in that text (Gemini). If the text does not contain the answer it says so instead of guessing. Use it for summaries, Q&A and checks over documents, emails and pages. Input: text, question; optional language. Fixed JSON fields: llm.extract.

LLM text generation / chat completion: a raw completion from your prompt with optional system message, max_tokens and temperature; Gemini by default, other configured models by provider and model. Use it for drafting, rewriting, translation, classification or any prompt, paid per call with no API key or account. Input: prompt. Answer grounded in your own text: llm.analyze.

Cluster-buy screen — issuers where >=N distinct insiders made open-market purchases within an M-day span; the classic bullish setup, precomputed

N reproducible 8-bit SFX variations of a preset in one call — the game-jam workflow (≤16 per call)

Shipping cost and delivery check for any Shopify store: the variant goes into a real cart session and the store quotes its shipping options to your destination. Returns options with prices and days, eligibility (or the store's reason, or the address fields still needed), subtotal and total before tax. No order is placed. Input: url, ship_to{country, province, postal_code}; optional variant, quantity.

Trading and portfolio math: returns and CAGR, volatility, Sharpe and Sortino, max drawdown, VaR/CVaR, beta, alpha and correlation vs a benchmark, SMA/EMA, RSI, Bollinger bands, Black-Scholes option price with Greeks, and the Kelly fraction, over prices you send or a ticker fetched live. Deterministic, every formula named, no LLM. Input: prices or symbol; optional metrics, benchmark, option, kelly.

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.

Predictive probability and regression engine: least-squares linear regression with standard errors, confidence and prediction intervals, a fitted normal distribution with quantiles and probability queries (P(y > t)), exact Student t and Jarque-Bera p-values. Points inline or from a BigQuery table. Deterministic arithmetic, no LLM: the same input always returns the same numbers. Input: points or table with x_column, y_column; optional metrics, predict_x, probability_queries.

Largest-context-window leaderboard: the 100 AI models with the biggest context windows, ranked descending — how many tokens each model can actually take, its max output tokens, modality support, and what those tokens cost. Compare GPT-5, Claude 5, Gemini 3 Pro, Llama 4 Scout and 2,000+ more on context capacity and price together. Refreshed hourly.

Cheapest vision/multimodal LLM leaderboard: the 50 lowest-cost AI models that accept image input, ranked by token price across every provider — GPT-5, Claude 5, Gemini 3, Llama 4, Qwen VL and more. Input, output and cache USD per 1M tokens with context window joined in. Answers 'what is the cheapest model that can read images?' in one call. Refreshed hourly.

Upcoming space launches worldwide from Launch Library 2 (The Space Devs): launch window (NET, window start/end), provider, pad and location, mission name/type/orbit, go/TBD status. Query: ?limit=10&search=falcon&provider=SpaceX&net_gte=2026-08-01&net_lte=2026-09-01 (all optional). Served from a 1h cache (upstream is rate-limited); count field gives the full upcoming total.

Daily river discharge forecast from the Copernicus GloFAS model (5 km grid) served via Open-Meteo Flood API, data CC-BY 4.0. Query: ?latitude=45.75&longitude=4.85&forecast_days=7 (1-210 days; daily=river_discharge,river_discharge_max for extra variables). Returns ISO date + m3/s arrays -- flood risk, inland shipping (Rhine/Danube) and hydropower planning. 6h cache.

Active weather alerts from the US National Weather Service (NOAA, public domain, real-time feed). Query: ?area=CA (2-letter state code) or ?point=34.05,-118.24; optional severity=Extreme|Severe|Moderate|Minor and event='Tornado Warning'. Returns up to 50 normalized alerts: event, severity, urgency, headline, affected areas, onset/expiry. count=0 means no active alert matches. 2 min cache.

Official risk register for any French commune from the GeoRisques GASPAR database (BRGM / Ministry of Ecological Transition, Licence Ouverte): flood, earthquake, industrial hazard, dam failure, ground movement, dangerous-goods transport, etc. Query: ?code_insee=31069 (INSEE commune code, not a postal code). Returns coded risk list with French labels. Slow-moving data, cached 7 days.

Consolidated MiFIR reference data for one ISIN, from the official ESMA FIRDS register (updated daily). Query: ?isin=FR0000120271 (required). Returns full and short instrument name, CFI code, issuer LEI, notional currency, relevant competent authority country, relevant market MIC and the deduplicated list of trading-venue MICs where the instrument is admitted. Cached 24h.