Web Search Research x402 offerings

Deprecated legacy alias — use /v1/firecrawl/scrape instead. $0.042 USDC per request. linkedin.com, lnkd.in, x.com, and twitter.com URLs are refused before payment (400).

One call loads a page in a real headless Chromium browser with JavaScript executed and returns its main content as clean markdown with the title, a word count and a report of any text the page hides from a reader. Use it for single-page apps and JavaScript-heavy sites where a plain fetch returns an empty shell.

Browser Use: AI browser automation agents in the cloud. POST a natural-language task and an agent navigates websites, fills forms, clicks buttons, extracts structured data, and completes multi-step workflows just like a human. Stealth-enabled remote browsers with CAPTCHA solving, residential proxies, live session view, and optional structured output. Payments top up your balance; managing your session is free — you only pay to open a new browser. Docs: https://docs.browser-use.com

Firecrawl v2 API proxy — scrape. JSON body matches https://docs.firecrawl.dev/api-reference/v2-introduction. Poll GETs for a job id you have are free and omit CDP and live-view URLs. POST /v1/firecrawl/interact (ttl max 120s) returns that session's URLs. Scrape-bound interact is paused (410). $0.042 USDC per request. linkedin.com, lnkd.in, x.com, and twitter.com URLs are refused before payment (400). Agent search: scrape, markdown, firecrawl, web scrape, scrape-lite.

Firecrawl v2 API proxy — map. JSON body matches https://docs.firecrawl.dev/api-reference/v2-introduction. Poll GET routes are free; POST/PUT/DELETE are x402. $0.010 USDC per request. Agent search: si…

Source keyword register for research hypothesis wording with verified-note crosswalk; literal vocabulary only. Reuses exactly one existing qualified meeting-notes request. Supplied source goes to the…

Compare Source keyword register for symptom vocabulary only, no diagnostic claim with verified-note crosswalk; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls.

Compare Source keyword register for forecast discussion wording with verified-note crosswalk; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witn…

Compare Source keyword register for forecast discussion wording with verified-note crosswalk; literal vocabulary only. against a bounded caller-supplied previous snapshot and return exact change witnesses. Baseline is caller supplied and is never authenticated as historical server output. Pure bounded timing/source-quote validation runs before payment. Exactly one current motor call, zero baseline provider calls.

Source keyword register for research hypothesis wording with verified-note crosswalk; literal vocabulary only. Reuses exactly one existing qualified meeting-notes request. Supplied source goes to the existing Groq model in the USA; existing processor disclosure and cost/margin retained. Notes quotes/owners/deadlines are verified by the unchanged motor first. Extra rules are deterministic; no semantic deadline resolution or specialist advice.

Agent researches a topic (web) and returns a concise, structured, cited brief. ?topic=. Pay-per-call in USDC on Base.

Bulk web search: up to 5 search queries in a single call, each returning ranked title, URL, and snippet, with the same locale, freshness, and news filters as the single-query web search. One paid call instead of five for research fan-out.

Fetch a public web page and return clean markdown (or structured JSON) — URL in, agent-ready content out, typically 80-85% fewer tokens than raw HTML. Handles redirects and compression.

Return the full detected technology stack for a domain. Every technology is mapped to a category with a confidence score. Includes stack_sophistication, stack_gaps, and competing_vendors derived intelligence. Billed per domain profiled.

Read any company page in real time and return clean structured content, links, metadata, and the detected tech stack. Data is fetched live from the source.

Read any company page in real time and return clean structured content, links, metadata, and the detected tech stack. Data is fetched live from the source.

Return the full detected technology stack for a domain. Every technology is mapped to a category with a confidence score. Includes stack_sophistication, stack_gaps, and competing_vendors derived intelligence. Billed per domain profiled.

Read any company page in real time and return clean structured content, links, metadata, and the detected tech stack. Data is fetched live from the source.

Canonical URL Decision — Decides for every URL variant of a page whether it is the canonical URL, gets a canonical tag to another address, a permanent redirect, a noindex, a 404 or 410, or cannot be settled from the facts given, answered as JSON only with the target and a short reason per URL. Follows Google's current canonicalization guidance on duplicate content - a redirect when the duplicate is deprecated, rel=canonical when it must stay reachable (tracking parameters, print views, a produc…

Detect whether a public page changed since the last hash, with a compact diff.

Detected changelog update history for one tracked vendor.

Place history research for genealogy and research agents. Returns the newspaper history of any town, city, or neighborhood.

Historical event research for research and historian agents. Returns how newspapers covered wars, disasters, social movements, and world events as primary sources.

Business history research for genealogy and research agents. Returns historical newspaper coverage of companies, shops, and industries from digitized archives.