Agent Hub

IP address and ASN lookup from the internet registries (RDAP): network name and range, owning organization, country, origin ASN, abuse contact email, registration dates and reverse DNS. Pass ip= (IPv4/IPv6) or asn=.

Developer toolbox in one call: sha256/sha1/sha512 hashes, base64/url/hex encode and decode, JWT decode, JSON format/validate, UUIDs, secure random numbers and passwords, regex test, slugify, word count and timestamp conversion. Also callable as GET with the same fields as query parameters.

Trusted current time (or a given moment) in UTC, unix seconds/ms, and up to 20 IANA time zones with local time, weekday and UTC offset. Also converts a timestamp between zones.

Geocode a place, landmark or street address to latitude/longitude with city, region, country, postcode, timezone and population where known. Cities via GeoNames, addresses and points of interest via OpenStreetMap.

Total value locked for a DeFi protocol (aave, uniswap, aerodrome, lido...) and/or a chain (Base, Ethereum, Solana...), with the chain's TVL rank.

Price history for any token contract: a time series at 5m to 1w intervals (up to 500 points) with open, close, high, low and percent change. Works for DEX-only tokens.

USD price and 24h change for any token by contract address (up to 30 at once) on Base, Ethereum, Polygon, Arbitrum, Optimism, BSC, Avalanche, Solana or World Chain. Covers long-tail DEX tokens that ticker-based price feeds miss.

Text embeddings for semantic search and RAG (BGE-M3, multilingual, 1024 dimensions). Up to 100 texts per call, one flat price. Also callable as GET with the same fields as query parameters.

Text to speech. Send up to 2000 characters and a language (en, es, fr, zh, jp, kr); get a natural-sounding WAV recording back. Also callable as GET with the same fields as query parameters.

Sentiment and tone classification for text (positive / negative / neutral with confidence, plus a one-line reason). Batch up to 20 texts per call. Also callable as GET with the same fields as query parameters.

Pay-per-call LLM chat completion on Llama 3.3 70B for harder reasoning, no API key. Same OpenAI-style messages body as /v1/llm. Flat price per request, up to 2k output tokens. 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.

Web search for AI agents. Send a natural-language query, get ranked results with title, url and snippet. Use when you need fresh information from the live web. Also callable as GET with the same fields as query parameters.

Public holidays for 100+ countries (optional state/province), plus business-day math: count business days between two dates, add N business days to a date, or check if a date is a business day.

Academic paper search across 250M+ works (OpenAlex): title, authors, year, venue, DOI, open-access PDF link, citation count and abstract. Sort by relevance, most recent or most cited.

Fact lookup for grounding: best-matching Wikipedia article summary plus structured Wikidata facts (website, founding date, birth/death dates, population, coordinates) and the source link. Any language edition.

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.

Wallet snapshot on Base or Ethereum: native ETH balance, nonzero balances of the major tokens (USDC, USDT, WETH, DAI, cbBTC, WBTC and more), transaction count and contract flag.

Current weather and up to 14-day forecast for any place name or lat/lon: temperature, feels-like, humidity, rain chance, wind, sunrise and sunset. Metric or imperial.

Solana token risk report (rug check) for any SPL or Token-2022 mint: mint and freeze authority, top-holder and developer concentration, serial-launcher check, Jupiter suspicious flag, liquidity, pool age, organic trading score, holders, price and market cap, a low/medium/high/critical rating and a plain-English AI verdict.

OpenAI-compatible moderation (Llama Guard 3): same response shape as OpenAI /v1/moderations with flagged, categories and category_scores, plus the raw Llama Guard codes. Up to 10 inputs per call. Also callable as GET with the same fields as query parameters.

OpenAI-compatible chat completions on Mistral Small 3.1 24B, tool calling and image input. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/mistral and pay $0.003 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, image input, streaming supported), up to 2048 output tokens. Also callable as GET with the same fields as query parameters.

OpenAI-compatible chat completions on NVIDIA Nemotron 3 120B, agentic reasoning with tool calling. Set your OpenAI SDK base URL to https://agents.torbrooknews.com/v1/nemotron and pay $0.01 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Also callable as GET with the same fields as query parameters.

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://agents.torbrooknews.com/v1/qwen and pay $0.002 per request with x402 instead of an API key. Same request/response shape as OpenAI (tool calling, reasoning, streaming supported), up to 4096 output tokens. Also callable as GET with the same fields as query parameters.

Official legal-entity registry lookup (GLEIF Global LEI Index, 200+ jurisdictions): legal name, LEI, active/inactive status, legal form, jurisdiction, company registration number and authority, legal and headquarters address, creation date and direct parent. Search by name (optionally country) or by LEI. For KYB, compliance and due diligence.

SEO audit of a page: score, list of issues, title and meta description length, canonical, robots, Open Graph, H1/H2 headings, images missing alt text, internal/external links, broken-link check on 25 links, word count and response time. Also callable as GET with the same fields as query parameters.

List every page on a website: reads robots.txt and all sitemaps (including sitemap indexes), with last-modified dates; falls back to on-page links. Up to 5000 URLs. Also callable as GET with the same fields as query parameters.

Document to text: convert PDF, Word (docx), Excel (xlsx/xls), ODS/ODT, CSV, HTML, XML or images to clean Markdown. Send a public file URL or base64 file plus filename (max 15 MB). Also callable as GET with the same fields as query parameters.

Speech to text (Whisper large v3 turbo). Send a public audio/video URL or base64 audio (max 20 MB); get the transcript, detected language, timed segments and WebVTT subtitles. Also callable as GET with the same fields as query parameters.

Extract structured JSON from any web page. Give a URL plus a JSON schema or a plain-English prompt describing the fields you want; a headless browser renders the page and an LLM fills the schema. Also callable as GET with the same fields as query parameters.