web-search-and-content

Use this when you need the current state of AI progress in one call: the latest reading of 129 public series (frontier benchmark scores GPQA/HLE/ARC-AGI/METR, Epoch compute trends, AGI odds on Polymarket/Manifold/Kalshi, model pricing, AI stocks and crypto, energy, space, robotics, biomed, research output). One JSON row per series: latest and previous value with dates, % change, signal quality, source URL. Free 3-row sample at /preview.

AI-generated social research: Twitter/X activity, Telegram presence, website analysis, mentions, sentiment, and entity verification.

Latest timestamped snapshot of 129 public AI-progress and technology time series: frontier benchmark scores (GPQA, HLE, ARC-AGI, METR task horizon), compute and training-run trends (Epoch), AGI prediction-market odds (Polymarket, Manifold, Kalshi), model pricing, AI stocks and crypto, energy, space, robotics, biomed, research output. Per source: latest and previous value with dates, % change, signal quality, source URL. No composite score. Free preview at /preview, menu at /.

What changed between two dated snapshots of 129 AI-progress and technology series: per source the from/to values and dates, absolute and % change, and whether a new observation landed. Covers frontier benchmark scores, compute trends, AGI prediction-market odds, model pricing, AI stocks and crypto, energy, space, robotics, research output. Ids are YYYY-MM-DD from the free menu at /. No composite score.

Find content gaps in supplied competitor pages

Extract structured data from any unstructured text into your own JSON Schema — structured-data /…

Descarga una página web y devuelve su texto limpio y legible (sin HTML ni scripts). Úsalo para que un agente lea el contenido de una URL pagando por llamada. input=URL http(s).

Web search, page extraction, and multi-hop web research.

OCR: extrae el texto de una imagen (JPG/PNG) o de un PDF, incluidos PDFs escaneados sin capa de texto. Motor local (Tesseract 5), idiomas español e inglés. Sube el archivo por multipart (campo 'archivo') o mándalo como 'archivo_b64' en el JSON. Opcional 'lang' (spa|eng|spa+eng).

Scrape the first page of any public Airbnb search URL (city, dates, guests, filters) into an array of listing cards with id, title, nightly price, currency, rating, review count and cover photo. Up to 18 results per call.

Extract one supplied HTML document into machine-readable evidence and cross-check it against itself. Returns title, metadata, canonical, robots directive, JSON-LD, resolved links, tables, readable text and content hashes. Reports a canonical that disagrees with the URL served, an Open Graph title that disagrees with the document title, a noindex directive, and absent title, description or structured data. Scripts are not executed and nothing is fetched.

Loads one https page in a real headless browser and performs up to eight steps on it: click, fill, select, check, uncheck, wait, wait_for_selector. Returns a per-step log saying what was attempted and whether it succeeded, plus the final URL, title, visible text, links, form structure and an optional screenshot as a base64 PNG. Three limits are part of the product, not accidents.

Product price lookup: give a product page URL, get the price, currency, stock status, name, SKU and images as clean JSON, read from the rendered page and the store's own schema.org data.

Extrae datos estructurados de un texto libre y los devuelve como JSON. Úsalo para parsear texto a datos. input=texto.

Render a URL through a headless browser and extract structured schema.org/Product JSON

Screenshot any web page: give a URL, get a 1280x800 JPEG of how it renders in a real browser, with its SHA-256, title and final URL. Use for visual checks, previews, archiving how a page looked, and showing a page to a vision model. $0.01 per capture; a page that fails to load or errors is not charged. For signed, timestamped evidence use /attest instead.

SerpApi Unified Search API https://serpapi.com - GET Perform real-time Google searches through SerpApi and receive structured JSON results instead of raw HTML. Retrieve web page titles, snippets, links, knowledge panels, and other SERP data directly from Google. Ideal for building SEO tools, keyword monitoring systems, or AI assistants that need live search data.

Read any web page as clean text: give a URL, get the page's visible text, title and final URL. Renders JavaScript pages in a real browser first, strips navigation and boilerplate, up to 50,000 characters. Use for web reading, research, RAG, page monitoring and feeding a page to an LLM (pairs with /summarize). $0.005 per page; a page that fails to load, errors or is empty is not charged.

Use this when you need AI progress as it stood on a past date: the reading of the same 129 series (benchmarks, compute, AGI prediction-market odds, model pricing, AI stocks, energy, space, robotics, research output) taken on YYYY-MM-DD. Dated ids are listed free at /. Same per-series shape as /ai-progress/latest, so you can diff dates yourself; /ai-progress/what-changed does the diff for you. Unknown id -> 404.

One call that searches the web and returns the readable text of the top pages — the whole "look this up" loop an agent otherwise writes by hand as a search plus N fetches plus N HTML cleanups. Pages are fetched concurrently under a deadline, stripped of navigation and scripts, and returned with their titles and source URLs.

Search the live web and get back ranked results with titles, URLs and snippets — no account, no API key, one payment per query. Built for agents that need to look something up mid-task: results are deduplicated by URL across every engine that answered, and the engines that produced them are named in the response so you can judge the coverage you actually received rather than assuming it was complete.

Extract the page's external links as markdown: fetches the URL, pulls every external links element and returns them as a Markdown list, with a count. Structured, one-element-type extraction for agents and pipelines; no browser needed. $0.01 per page.

Does a website use Make (Integromat)? Fetches the page (homepage for a bare domain) and matches Make (Integromat)'s fingerprints in the HTML and response headers, returning yes/no with the evidence snippet and the category (automation). Technographics for sales, competitor research and migration planning, one technology per call. $0.01 per check.

Does a website use TrustArc? Fetches the page (homepage for a bare domain) and matches TrustArc's fingerprints in the HTML and response headers, returning yes/no with the evidence snippet and the category (consent). Technographics for sales, competitor research and migration planning, one technology per call. $0.01 per check.