Quick AI token verdict: a 2-3 sentence plain-English risk summary plus risk level and red flags for any token on Base, Ethereum, Polygon, Arbitrum, Optimism or Solana. Built on honeypot sell simulation and tax checks (EVM) or mint/freeze authority and holder concentration (Solana). Half the price of the full report.

Macroeconomic indicators for any country: GDP growth, inflation, unemployment, GDP, GDP per capita, government debt, budget balance, current account and population (IMF World Economic Outlook, including forecasts), plus World Bank interest rates, exports, FDI and more; ECB policy rate for euro countries.

US public company filings and fundamentals from SEC EDGAR: latest annual revenue, net income, EPS, assets, liabilities, cash, shares, plus recent 10-K/10-Q/8-K filings with links. Query by ticker or CIK.

US imports and exports from official Census trade data: by product (HS code) the top partner countries with value, share and year-to-date; by country the trade balance and top products; or US totals, for the latest month or any month.

OpenAI-compatible chat completions on Alibaba Qwen3 30B mixture-of-experts, thinking model with tool calling, the cheapest chat here. Set your OpenAI SDK base URL to https://agentrxi.com/v1/qwen and pay per token with x402 instead of an API key: $0.153 per million input and $1.005 per million output tokens, minimum $0.002 a call, at most $0.0072. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool

Address verification and standardization worldwide: parsed components (house number, street, city, state, postcode, country), confidence to building, street or city level, a plain verdict, coordinates, timezone and alternatives.

Static map image (JPEG) of a place or up to 15 numbered markers, in 7 styles and any size up to 1600 px, returned as base64 and a data URL ready for reports, emails and chat.

Any public-domain FRED economic time series by id (UNRATE, CPIAUCSL, GDP, DGS10, thousands more): observations with optional transforms (change, % change, % change from a year ago), frequency aggregation and date range, plus title, units and notes.

How many businesses of a kind are in a US county, state or ZIP: establishments, employees, annual payroll and average pay by industry (keyword or NAICS code), plus businesses per 10,000 residents for market sizing and competition checks.

Has anyone hit this error? Searches GitHub issues for an error message (exact phrase first, then keywords): title, repo, open or closed, comments, labels, link and an excerpt, most-discussed first.

Chart images: bar, line, pie or scatter charts as PNG or SVG from your numbers, with title, labels, several series and legend. Ready to drop into a report or message. Also callable as GET with the same fields as query parameters.

OpenAI-compatible chat completions on Meta Llama 4 Scout, multimodal (image input) with tool calling. Set your OpenAI SDK base URL to https://agentrxi.com/v1/llama4 and pay per token with x402 instead of an API key: $0.81 per million input and $2.55 per million output tokens, minimum $0.002 a call, at most $0.0145. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, image input, streaming

Translate text between about 100 languages (M2M-100). One text or a batch of up to 20; give target_lang and optionally source_lang (default en). Priced by size: $0.004 + $0.0007 per 1,000 characters. Also callable as GET with the same fields as query parameters.

OpenAI-compatible chat completions on Zhipu GLM 4.7 Flash, reasoning and tool calling. Set your OpenAI SDK base URL to https://agentrxi.com/v1/glm and pay per token with x402 instead of an API key: $0.18 per million input and $1.2 per million output tokens, minimum $0.002 a call, at most $0.0082. The 402 quotes your request's maximum; "upto" payers are charged only the tokens used. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 409

Scrape text and attributes from a rendered web page using CSS selectors. Returns every match per selector. Also callable as GET with the same fields as query parameters.

Fetch any public web page with a real headless browser (JavaScript rendered) and return clean Markdown. Use to read articles, docs, product pages or SPAs that a plain fetch cannot render. Also callable as GET with the same fields as query parameters.

Full-page PNG screenshot of any public URL rendered by a real browser. Returns PNG bytes. Also callable as GET with the same fields as query parameters.

Ask a question about an image (Moondream 3.1 vision model): read signs and screens, count things, describe a scene or check a photo. Without a question it writes a caption (short, normal or long). Priced $0.003 + up to $0.003 by max_tokens (default 512, max 1,024). Also callable as GET with the same fields as query parameters.

Summarize any web page or long text. A headless browser renders the URL, an LLM writes a faithful summary: short (2-3 sentences), medium (one paragraph) or bullets. Also callable as GET with the same fields as query parameters.

Verify an email address: syntax check, domain MX lookup, disposable-domain and role-account flags. Use before sending or storing an address.