Web & Data

Newest headlines from a deduped, tiered 972-feed direct portfolio (primary sources + wires/majors + trade press + Hacker News + gated GDELT), newest first, up to 100 per call — filter by category, source, and language; every article carries tier, categories, summary/author/image when present, and a provenance-labelled tone

Web scraping / web page to clean text: any URL rendered in a real browser (JavaScript pages included) and returned as readable text with title, description and links. Use it to read an article, docs page or product page before summarising or extracting. Input: url. Raw status, headers and body: fetch.raw. A question answered from the page: research.brief.

HTTP fetch / GET any URL: exactly what the server sent, status code, headers and body, plus the final URL after redirects. Every status is a result, so a 404 or 500 from the target is delivered, not failed. Use it for API checks, uptime probes and raw HTML. Input: url. Readable text from a rendered page: extract.page.

Web search with an answer: real-time search of Brave's independent web index, answered from the current results only, with every source URL and title returned, never the model's memory. Use it when an agent needs up-to-date information, latest news, prices or facts from the web. Input: query; optional language. Raw result list (SERP): search.results. Sources read in full with citations: research.web.

Extractive summary of any text, computed offline (no LLM): ranks sentences by term significance and returns the top ones in reading order. Set how many sentences you want. Key-less, instant, $0.002.

Extract the top keywords and key phrases from text (frequency, stopword-filtered) plus structured entities by pattern — emails, URLs, @mentions, #hashtags, phones, money, dates and 0x crypto addresses. Offline, key-less, $0.002.

Research brief with citations: a quick, sourced answer to any question or topic. Use before writing, deciding, or searching deeper. Pass q (question). Returns a summary, 3-6 cited bullets and sources (official docs, Wikipedia, Stack Overflow, GitHub, papers) with URLs and dates; off-topic sources dropped. 0.01 USDC (Base/Polygon/Arbitrum/Solana/Avalanche/Sei). Errors are never charged: 400 bad input, 422 nothing found or target unreachable, 503 busy.

Relevant pages API - list a domain's best-performing pages in Google, each with page-level organic and paid metrics: ranked keyword count, estimated traffic (ETV), traffic cost and position buckets (pos1/top3/top10/top100). For finding a site's top content, competitor content research and page-level SEO audits. Unknown domain returns empty results.

Backlink anchor text API - list the anchor texts pointing at a domain, each with how many backlinks, referring domains and referring pages use it, the dofollow/nofollow split, DataForSEO rank, spam score and broken-link count. For anchor-text distribution analysis, over-optimization/penalty audits and link-building research. Unknown domain returns empty results.

Given a set of specific page URLs, find the Google keywords those pages jointly rank for, with each page's position, URL and estimated traffic (ETV) per keyword, plus search volume, CPC, competition, difficulty and intent. Page-level, not domain-level. Optional exclude_pages narrows to keywords the pages rank for that others do not.

SYNTHORA fed-watch: US reference-rate funding pulse — SOFR/EFFR/TGCR/BGCR/OBFR with volumes, percentile dispersion and the SOFR-EFFR spread (the funding-stress signal before it hits the news). Cross-check of 5 independent official NY Fed series. The input for Fed/CPI prediction markets. Free official source, no key. $0.01 USDC x402 Base.

Voice-of-customer / product complaints digest for AI agents - pass a product or brand, get clustered pain points, feature requests and praise mined from live X posts, with verbatim quotes and URLs. Product research, competitor research, churn signals, roadmap input. ?product=<name or handle>. Raw tweets + trend summary instead: /x/digest $0.05.

Page speed and page weight audit of a web page from one real browser load: total bytes transferred, HTTP request count and DOM node count, measured rather than estimated, with findings when the page is heavy. Page-weight signals, not Core Web Vitals.

SEO audit of a web page (on-page SEO check) for any live URL or raw HTML: title tag, meta description, H1 heading structure, canonical link, OpenGraph and social tags, JSON-LD structured data, html lang attribute. Rule-by-rule findings with severity and what is missing or malformed.

Search the persisted Wirecutter recommendation database by product type, pick name, review title, category, and model tokens. Search is lexical today; pass concise, spelling-corrected product/category nouns instead of vague natural-language intent.

Compute the SHA-1 hash (hex digest) of an input string. Deterministic fingerprints and git-style content identifiers.

EIP-55 mixed-case checksum for a 20-byte EVM (Ethereum/Base) hex address, via Keccak-256. Normalize and verify addresses before a transfer.

Generate a random RFC 4122 version 4 UUID. Unique identifiers for records, requests and idempotency keys.

Fetch a URL and return a structured LLM brief: summary, key points, entities, topics, sentiment, notable facts — one call instead of fetch + reason.

Get OHLCV candlestick data for charting and analysis

Run HTTP + SSL + DNS + domain-expiry in one call and return a combined health snapshot. The single pre-flight check to run before crawling, deploying to, or depending on a site — cheaper and one round-trip instead of four.

Convert CSV text (first row = headers) into a JSON array of row objects. Parse spreadsheets and exports into structured data.

Diff two texts offline (LCS-based): the added and removed lines, a count of changed line-pairs, added/removed word tallies and a 0-1 similarity ratio. Key-less, instant, $0.002.

24h long/short liquidation totals per symbol, merged across venues, full universe.