Web & Data

Find pages semantically similar to a given URL.

Get an AI-generated answer to a question grounded in live web search results.

Neural and keyword web search. Optional category filter: company, research paper, news, pdf, github, tweet, personal site, linkedin profile, financial report.

Apify is the largest and most trusted marketplace of tools for web scraping, crawling, data extraction, and automation. Use these tools, called Actors, to extract structured data from social media, e-commerce sites, search engines, maps, travel sites, or any other website. Turn the open web into a real-time data source for your research, lead generation, and monitoring.

Screens and filters perpetual futures contracts based on specified criteria.

Look up VAT rates for EU/EEA countries. Returns standard, reduced, zero-rated categories. Supports category-specific queries.

Detailed TVL + breakdown for a single protocol. Pass slug as `/v1/defillama/protocol/{slug}` (e.g. `aave`, `uniswap`).

Skim: clean reader — URL to agent-ready markdown + structured metadata, ~4x smaller than raw HTML.

Extract article / main content from any URL or PDF to clean, LLM-ready Markdown (web scraper / reader / html-to-markdown) — strips scripts, nav, ads, and boilerplate while preserving headings, links, lists, tables, code blocks, and blockquotes; extracts the text layer from PDFs. Returns Markdown body, title, word count, and a quality grade so agents can read articles and documents without a browser or paid scraping service.

Extract article / main content from any URL or PDF to clean, LLM-ready Markdown (web scraper / reader / html-to-markdown) — strips scripts, nav, ads, and boilerplate while preserving headings, links, lists, tables, code blocks, and blockquotes; extracts the text layer from PDFs. Returns Markdown body, title, word count, and a quality grade so agents can read articles and documents without a browser or paid scraping service.

Retrieves media content related to tracked events or incidents.

Returns a single random fact as JSON in exchange for a micropayment.

Detailed TVL + breakdown for a single protocol. Pass slug as `/v1/defillama/protocol/{slug}` (e.g. `aave`, `uniswap`).

Extract and classify all hyperlinks from a web page — internal vs external using eTLD+1 domain matching. Returns up to 200 internal and 200 external links with counts. No web crawler setup needed. Accepts USDC payments on Base and Solana

Demo: weather-driven delay-risk score for 5 fixed US locations. Same schema as the full /api/delay-risk endpoint. Try before you buy.

Extract clean, readable text from any web page — removes navigation, ads, scripts, and boilerplate. Dual-engine extraction with JS-rendered page fallback for SPAs and dynamic content. Returns content with title, author, word count, language, and reading time. No headless browser or scraping library needed. Accepts USDC payments on Base and Solana

Daily weather forecast (1-7 days) by city name — max/min temperature, precipitation amount and probability, peak wind speed per day. Automatic geocoding from city name to coordinates. Structured JSON ready for immediate use in agent workflows. No API keys, no coordinate lookups, no setup needed. Accepts USDC payments on Base and Solana

Returns information about strike events, categorized by type.

Fetch any URL and return clean Markdown with metadata (title, byline, excerpt, siteName, lang). Uses Mozilla Readability + Turndown. Built for AI agents doing RAG, content summarization, and research workflows. Drop-in alternative to Jina Reader and Firecrawl, with pay-per-call USDC pricing via x402. Accepts payment on Base or Solana — either network works.

Executes search queries across Solana blockchain data.

invinoveritas /signals/full — the live Hyperliquid perps read our own bot enters on, recomputable per coin from the raw metrics we return (funding + 24h delta,

LastLook Data — EFFR vs IORB spread. Shows where the effective Fed funds rate trades relative to interest on reserves.

Web page to clean markdown. Converts any URL into LLM-ready markdown plus structured metadata — a keyless alternative to Firecrawl.

Exa neural search - AI-native web search with structured results and citations