Web Search Research x402 offerings

Fetch a public URL and return redirect, metadata, cache validators, and a SHA-256 content fingerprint.

Batch x402 endpoint reliability: factual delivery measurements (uptime, valid-402 rate, latency, last status) for an agent's whole tool list of x402 endpoints in one paid call. Endpoints with no stored history are probed live, so every billed URL returns real facts. Sweep every endpoint you depend on before relying on them. Billed per endpoint, with volume discounts at 10+/50+/100+ URLs. Facts only — not an endorsement or rating.

Read 2 to 5 pages whose URLs you already know in one call, each as clean Markdown with title and description, fetched in parallel. Cheaper and faster than calling web-scrape once per URL; for 6 to 20 URLs use web-scrape-batch. A failed page is reported with its error while the others still return; charged only if at least one page was read. To find URLs first, use site-map (one site) or search-read (a question). Params: urls (1 to 5, required), max_chars per page (500 to 30000, default 6000).

Prüft am Objekt artikel den Befund vorhandene Meta-Beschreibung.

Detects bias and slant in news articles using AI analysis.

Checks media mentions and RSS news buzz matching the company name.

Checks media mentions and RSS news buzz matching the company name.

Real-time web and news search powered by xAI Grok with live data access.

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

Extract full text content from specific URLs. Priced at $0.002/URL plus a $0.001 transaction fee per call — total = urls.length × $0.002 + $0.001.

Chat completions with 33+ AI models including GPT-5.5, Claude Opus 4.6, and more. Supports OpenAI-compatible format.

Grok Live Search API - real-time web and news search

Find pages semantically similar to a given URL.

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

Condense one web page into a short summary. Give a URL; Bob reads the page with Firecrawl and returns an 80-word summary with key points, not the page text (use /extract for the text itself). Typical response 3 to 6 seconds. If the page cannot be read in time you get an error and are not charged.

Ask any factual or market-research question. Searches the live web with Tavily and Exa, extracts the most relevant page with Firecrawl, and returns a short synthesized answer with source URLs. Typical response 4 to 8 seconds. If it cannot answer in time you get an error and are not charged.

Plain web search. Returns ranked results (title, URL and a short snippet) for a query, up to 10, optionally limited to a publish-date range with since and until (YYYY-MM-DD). No AI-written answer, so it is fast: typically under a second. If it cannot return results you get an error and are not charged.

Fact-check a claim against the live web. Searches with Tavily and Exa, reads the best page with Firecrawl, and returns a verdict (supported, contradicted or unclear), a short explanation and source URLs. Typical response 4 to 8 seconds. If it cannot answer in time you get an error and are not charged.

Get the full text of one web page. Give a URL; returns the page's own main content as clean markdown (up to 8,000 characters) with navigation and ads removed, unchanged and not summarized (use /summarize for a short version). Typical response 2 to 5 seconds. If the page cannot be read you get an error and are not charged.

Search audiobookbay.lu for audiobooks. Returns up to ~12 result entries with slugs that can be passed to /api/audiobooks/details for magnet links.

Audits the JSON-LD structured data on one public web page: P1 for no schema or missing required properties, P2 for a low rich-result score, each with the properties to add. Call it when a page is missing rich results in Google or before publishing a page that should earn them. Input: url. Returns in seconds. Errors: 400 invalid input, 502 audit failed, 504 timed out. You are not charged for an error response.

Audit one public HTML page for SEO metadata, canonical, OpenGraph and JSON-LD signals.

Check whether a list of URLs, or every link on a page, works: HTTP status, final URL after redirects and broken links first. Up to 50 URLs per call, checked in parallel.

Pay-per-request access to Replicate AI and Cloudflare Browser Rendering. No API keys, no subscriptions.