Web & Data

OpenAI pre-IPO fundamentals as JSON: FY2025 revenue, monthly revenue, ChatGPT users and subscribers, March 2026 round size and post-money valuation, new round target and valuation in talks, SoftBank bond financing and stake, valuation-to-run-rate multiple. Each number has its own source URL, verification grade and value type.

Perplexica AI Search

Returns news articles or updates.

Fetch a reviewed public page and return its title, every meta and Open Graph tag, and the canonical URL. No JavaScript is executed and no script content is read. Returns the licence and creator for the content alongside it, so reuse terms travel with the result.

Decode EVM calldata into typed function args with deterministic risk flags (unlimited approvals, admin actions)

Watch up to ten reviewed public pages in one call. Supply the previous text hashes and it returns which pages actually changed, not ten hashes for you to compare. Hashes both the raw HTML and the visible text, so markup churn can be told from a real content change. A page that cannot be fetched is named individually and does not fail the batch.

Transcribe a public HTTPS audio or video URL into structured JSON with timestamps, optional speaker diarization, confidence metadata, and actual-duration settlement.

Fetch a reviewed public page and return its HTML tables as arrays of rows and cells. Bounded to ten tables, fifty rows each and twenty cells per row, and every bound that is reached is named in the warnings so a truncated table is never mistaken for a short one.

Retrieves or manages categorization tags associated with vault protocols and strategies.

Public-Domain Book Search (Project Gutenberg, 75k+ books). Search 75,000+ public-domain books on Project Gutenberg by title or author: book id, title, author, download count and a link to the full-text endpoint.

Fresh machine-readable Polymarket/Kalshi market pulse and snapshot hash. No trade execution.

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.

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

Fetch a reviewed public page and return its links with resolved absolute URLs and anchor text, the canonical URL, the declared meta robots directive, and how many links leave the host. Relative hrefs are resolved against the page, so a caller never has to guess a base.

Fetch a reviewed public page and return every JSON-LD structured-data block it declares, parsed. No script is executed. A block that is malformed is reported as a named warning rather than being silently dropped, so a caller can tell an empty page from a broken one.

Fetch a public http(s) URL (?url=...) and return best-effort clean text/markdown; SSRF-safe with size/time caps

Is this paid endpoint answering right now? Returns whether it serves a payment challenge, how many well-formed priced offers it carries, which warnings would actually break a payment as opposed to merely making the call harder to construct, and a single payable_now flag. Reports only what was observed; it makes no judgement about the seller.

Fetch a reviewed public page and return SHA-256 hashes of both the raw HTML and the visible text, with byte and character counts. Two hashes because they answer different questions: the HTML hash moves when anything at all changes, the text hash moves only when the content a reader would notice does.

Fetch a reviewed public page and return its readable content as Markdown, with headings and list structure preserved. Script, style and template content is removed, and nav and aside elements plus anything marked role="navigation" are excluded from the text. Returns the licence and creator, because this content is reusable only on those terms. Truncation at any bound is reported, never silent.

New activity for a Base address since your cursor (stateless watch)

Genera FAQ (preguntas + respuestas) de un texto/tema. Para docs/soporte. input=texto o tema.

Investiga un tema en la web y devuelve una síntesis con fuentes citadas (títulos + URLs). Úsalo para research pagado por consulta cuando un agente necesita información actual con fuentes. input=tema a investigar.

Verifica una afirmación (fact-check) con veredicto y razón. Nivel verificación. input=afirmación.

Convierte un texto en un vector (embedding) para búsqueda semántica, RAG, clustering o memoria. El bloque base que todo agente de IA necesita. Alto volumen. input=texto.