Every agent-payable API.

Current weather and a daily forecast (up to 9 days) for any city, address or coordinates: temperature, min/max, humidity, wind, clouds, pressure, sky and precipitation, from the Norwegian Meteorological Institute. Use for travel, events, logistics or energy planning.

Weather forecast for any latitude/longitude: current conditions plus up to 7 local-day summaries (min/max temperature, precipitation, max wind, weather symbol) in the place's own time zone. Data from MET Norway (CC BY 4.0). For travel, tourism, events and logistics agents.

Daily high/low, precipitation, and conditions for the next N days at any lat/lon (Open-Meteo).

Weather forecast and alerts: give a latitude and longitude in the US, get the 7-day forecast (temperature, rain chance, wind) and any active weather alerts from the National Weather Service.

Weather current + short forecast via Open-Meteo (keyless). Lat/lon required. Data only — not advice.

weather-forecast: Current temperature and precipitation for any city (by name or lat/lon), powered by Open-Meteo.

Weather forecast API: current conditions (temperature, feels-like, humidity, wind, weather code) plus a 3-day daily forecast (highs, lows, precipitation probability) for any latitude/longitude worldwide, as structured JSON. Use for travel planning, logistics, event scheduling, and assistant agents. Cached 10 minutes.

Get current weather conditions and a one-to-seven-day forecast for a geocoded location from Open-Meteo.

Weather forecast for any coordinates worldwide: current conditions plus a condensed hourly forecast (temperature, wind, humidity, precipitation, condition codes) and a will-it-rain summary. Official MET Norway model data (the institute behind yr.no) — commercial use permitted, attribution included. $0.002 per call.

Weather Now + Forecast: current weather + 3-day forecast for any city Executed deterministically by the AmanChain node against live consensus state (real blocks, pools, balances) — paid per call via x402, settled in USDC on Base. Input: JSON body {"serviceId":"aman-weather","request":"<input>"}. No account, no API key.

Weather for any city or point on Earth (city name, or latitude and longitude): current temperature in Celsius, conditions (clear, cloudy, rain, snow), precipitation in mm, wind, humidity, cloud cover and air pressure, plus an hourly forecast for up to 48 hours. Data from the Norwegian Meteorological Institute; city names resolve via Wikidata. Use for travel and event planning, logistics, agriculture and any agent that needs the weather.

Weather, air quality (AQI, PM2.5) and nearby earthquakes for any place on Earth in one call, plus a clear/caution/hazard verdict with reasons. Use it to check conditions or hazards at a location; many locations per run. Keyless (Open-Meteo + USGS); webhook alerts. Up to 3 items per call; failed lookups are not charged.

Semantic web search (understands intent, not just keyword matching) — for an agent that needs current information, facts, or sources beyond its training data. Returns ranked results (title/url/content snippet) plus an optional AI-generated direct answer, via Tavily. JSON body: {query: string, num_results?: integer 1-10 (default 5)}.

Use when an agent needs a sourced answer to a question from the live web in one call. Input: q (question), optional time_range (day, week, month, year). Output: JSON answer (English, inline [n] citations), citations [{url, title, quote}], confidence, notes, sources read. Searches, reads the top 4 pages itself and answers only from them. Provider or model failure is not charged. Example: ?q=what+is+the+x402+payment+protocol

AI-generated answers powered by Exa web search. Ask a factual or open-ended question and receive a synthesized answer with source citations.

Web Answer with Sources

Web buzz for a coin/token: total count of web mentions (news, blogs, forums) plus an emotion breakdown (happiness, anger, love, sadness, fun) and a 0-1 positivityScore. A social/editorial signal distinct from the market Fear and Greed index and news lists.

Browser screenshot, rendered HTML, metadata, PDF and signed artifact receipt. Service-clock time; no independent timestamp or completeness guarantee. Exact-host loading; other-host assets and redirects excluded.

Web scrape URL to clean Markdown and JSON text extraction ($0.002 USDC) — Scrape any webpage URL to clean Markdown (up to 64 KB), title, and metadata with zero charge on failure.

Use to extract the main article or document text from a single-page URL. Not for homepages or hubs (Web Index Cleaner) and not a link inventory (Link Extractor). Server HTML only; JavaScript is not run. Output is text or markdown. If the requested extract has no main content, the other profile is tried once in the same request. The HTTP body has correlation_id and data. The item array is data.results.

Web content extraction: fetch any public web page and get its readable article content as clean markdown — boilerplate, nav, and ads stripped automatically. For "get me the readable text of this page" requests. Honors robots.txt and Content-Signal/aipref declarations (explicit disallow returns an unpaid 403). SSRF-guarded, 2MB cap.

Retrieve clean content from one webpage using Exa. Choose full text, query-focused highlights, or an AI-generated summary, with page metadata and retrieval status.

Retrieve deterministic evidence from a public HTTPS page

Use when an agent needs specific fields from a web page as JSON. Input: url, schema (URL-encoded JSON Schema, object root, max 30 properties, depth 3, 3,000 chars). Output: JSON data validated against the schema (null when not on the page), title, finalUrl. SSRF-safe; noai pages refused; bad schema refused before payment. Fixed schema: /v1/docs/extract. Example: ?url=https://example.com/&schema={"type":"object","properties":{"title":{"type":"string"}}}

Web extraction: every output you ask for in `formats`, in one call.

Web extraction for AI agents: URL to clean Markdown + metadata, automatic JS rendering, robots.txt respected. No API key.

Use to extract readable text from a homepage or hub URL. Not a single-article extract (Web Content Cleaner) and not a structured link list (Link Extractor). If the requested extract has no main content, the other profile is tried once in the same request.

Summarize any web page: send a URL, get a factual summary that starts with what the page is, followed by the key facts, numbers and conclusions as bullet points. Reads the page (HTML to Markdown) and summarizes it with Claude Haiku 5.5. Options: length short (60 to 90 words), medium (150 to 220) or long (350 to 450); language for the summary (default: the page language, e.g. German); focus to steer it (e.g. "pricing and plans").

Summarize a web page: give a URL, get a short summary of the page written by Claude, with its title and final URL.

Web page to clean text: title, description, headings, links and readable text from any public URL — Genesis402 / UnyKorn Operator Network

Web page to markdown: read any public URL as clean, LLM-ready Markdown. Strips nav, ads and cookie banners; returns main-content Markdown plus title, author, date and word count. Charged only on success.

Read any public web page and get its main content as clean Markdown (menus, ads and footers removed) with title, author, publish date and language. Use when you need to read, quote or summarise an article, docs page or blog post from a URL. Not charged if the page fails.

Web page to markdown: give a public URL, get its main content as clean Markdown for LLMs (navigation, footers and scripts removed) with title, canonical URL, language, publish date and links. Use when an agent needs to read, quote or summarise a page. Respects robots.txt, ai.txt and noai; no paywall bypass; refusals are not charged. Signed receipt.

Use when an agent already has a URL and needs the page as clean Markdown (boilerplate removed, tables kept). Input: url, optional max_chars (500-60000), flags=1 for rule-based prompt-injection signals. Output: JSON markdown, title, language, finalUrl, chars, truncated. SSRF-safe; pages opting out with noai are refused. English brief: /v1/web/read/brief. Search+read: /v1/web/search-read. Example: ?url=https://example.com/

Use when an agent needs a page in any language (Korean, Japanese, etc.) read and briefed in English. Input: url, optional max_chars, flags=1. Output: JSON markdown, title, plus brief {headline, summary, key_points, entities, topics, source_language, content_type}; fixed schema, cached by content. Model outage or daily cap is refused before payment. Example: ?url=https://example.com/

Use when an agent has several URLs (search results, citations) and needs them all as Markdown at once. Input: urls (1-5 public URLs separated by spaces), optional max_chars per URL (500-20000), flags=1. Output: JSON results[] in input order, each status ok (markdown, title, finalUrl) or error (code, message). Charged once if at least one page is read. Example: ?urls=https://example.com/ https://example.org/

Read 2 to 5 pages whose URLs you already know in one call, each as clean Markdown with title and description, fetched in parallel. Cheaper and faster than calling web-scrape once per URL. A failed page is reported with its error while the others still return; charged only if at least one page was read. To find URLs first, use site-map (one site) or search-read (a question). Params: urls (1 to 5, required), max_chars per page (500 to 30000, default 6000).

Web Reader — Fetch a public web page and return clean Markdown an agent can read.

Web research in one call: search, read the top 8 pages in full (clean markdown, each with a prompt-injection check) and extract the 15 key passages that answer the question, with sources and domains. For agents that need evidence from several sites, not one snippet. Cheaper than a research run on Exa or Firecrawl.

Default tool for reading ONE web page whose URL you have: returns clean Markdown (title, meta description, main content with headings, lists and links). The fastest and cheapest way to give an LLM the content of a page. If a JavaScript app comes back nearly empty, set render:true (real browser, slower, plain text) or use webpage-reader. For 2 to 5 URLs use web-read-batch, for a whole site site-crawl, and if you have a question but no URL search-read.

Web scraping / URL fetch: retrieve any web page and return clean, LLM-ready markdown text. Strips boilerplate, ads, and navigation. Stealth HTTP client bypasses common bot blocks. Cheapest way to read a webpage.

Web scraping API for AI agents — extract clean text and metadata from one safe public HTTPS URL in a single x402 call.

Use when an agent must see how a page looks (layout, charts, visual QA, previews), not just its text. Input: url, width (320-1920, default 1280), full_page=1 for the whole page, format png or jpeg (default). Output: JSON imageBase64 (decode to the image), contentType, bytes, viewport. Renders JavaScript. Daily cap or bad URL refused before payment. Example: ?url=https://example.com/

Use when an agent needs current web results for a query. Input: q, optional max (1-10, default 5), time_range (day, week, month, year). Output: JSON results with title, URL and date when known, provider and retrieval time. For page text use /v1/web/search-read. Provider failure is not charged. Example: ?q=x402+payment+protocol&max=5

Quick factual lookup: a plain-language summary (abstract) plus up to 5 relevant links from Wikipedia. Best for people, places, concepts, history and science. Returns links, not page content: to get the content of the top results in the same call, use search-read. Not for breaking news: use news-search. Params: query (required).

General web search reselling the Tavily Search API: query the live web and get back ranked results (title, URL, snippet, relevance score) plus an optional short synthesized answer, with basic or advanced search depth and optional domain include/exclude filters.

Web search API - live Google (default) or Bing SERP for a query: search engine results returned as ranked organic hits with title, URL, domain and snippet, localised by location and language. A google search api / serp api for agents: search the web, live web search for grounding, RAG and web lookup.

Web search (Google results via Serper): top 10 organic results + answer box + knowledge graph. Query: ?q=&gl=&hl=

Web search API (SERP) with page text: like a search API key, pay per call. Pass q, optional n (1-10, default 5). Returns ranked results with title, url, domain, snippet, publish date and up to 1500 chars of cleaned main text from each page, fetched live, so agents can answer without opening links. Fresh results for news, docs, products, local businesses, definitions. 0.01 USDC/call; failed calls are free.

Web search that reads the results: give a query, get the top web results plus the full text of the top 1-3 pages, each read in a real browser. For research, RAG and fresh answers in one call.