Web Search Research x402 offerings

Change watch for extract zip codes us from page: runs the check, compares it with the result from your previous call for the same url (kept 90 days) and returns the current answer, changed true/false, the fields that changed with before/after values, and when it was last seen. Schedule it to be alerted when this changes. $0.02 per check.

AI Web Extractor — turn ANY url into clean, LLM-ready markdown. POST {url}; get the main content as markdown (boilerplate/nav/ads stripped) with title, description, and links. The scrape / read / url…

Extractive summary without AI: picks the most representative sentences (term frequency and position scoring) and returns them in original order, with the reduction percentage. Deterministic and instant.

10-sentence extractive summary of a page: sentences are scored by keyword density (no LLM, no hallucination), the top 10 are returned in original order with the page title. Fast, deterministic gist for triage and previews. $0.01 per page.

Bulk extractive summary 10 sentences: up to 20 urls in one call, processed concurrently, results in input order with a per-item error field and a failure count. Same answer per item as the single endpoint. Batch enrichment for agents that hold a list. $0.10 per batch.

Change watch for extractive summary 10 sentences: runs the check, compares it with the result from your previous call for the same url (kept 90 days) and returns the current answer, changed true/false, the fields that changed with before/after values, and when it was last seen. Schedule it to be alerted when this changes. $0.02 per check.

3-sentence extractive summary of a page: sentences are scored by keyword density (no LLM, no hallucination), the top 3 are returned in original order with the page title. Fast, deterministic gist for triage and previews. $0.01 per page.

Bulk extractive summary 3 sentences: up to 20 urls in one call, processed concurrently, results in input order with a per-item error field and a failure count. Same answer per item as the single endpoint. Batch enrichment for agents that hold a list. $0.10 per batch.

Change watch for extractive summary 3 sentences: runs the check, compares it with the result from your previous call for the same url (kept 90 days) and returns the current answer, changed true/false, the fields that changed with before/after values, and when it was last seen. Schedule it to be alerted when this changes. $0.02 per check.

5-sentence extractive summary of a page: sentences are scored by keyword density (no LLM, no hallucination), the top 5 are returned in original order with the page title. Fast, deterministic gist for triage and previews. $0.01 per page.

Bulk extractive summary 5 sentences: up to 20 urls in one call, processed concurrently, results in input order with a per-item error field and a failure count. Same answer per item as the single endpoint. Batch enrichment for agents that hold a list. $0.10 per batch.

Change watch for extractive summary 5 sentences: runs the check, compares it with the result from your previous call for the same url (kept 90 days) and returns the current answer, changed true/false, the fields that changed with before/after values, and when it was last seen. Schedule it to be alerted when this changes. $0.02 per check.

Compare a spot KRW price for one symbol across Upbit and Bithumb's public, account-free ticker APIs. Required symbol (1-10 letters/digits, uppercase-normalized); optional exchange (all, upbit, or bithumb; default all). Returns per-exchange price, rolling 24h volume and notional, normalized change rate with its exchange-specific basis, and upstream timestamp, plus an absolute/percent spread when both exchanges succeed. At least one requested exchange must return a fresh, well-formed quote or the call fails and does not settle.

Fetch one public HTTPS page and return bounded clean readable text, title, author, publish date, excerpt, word count, redirects, and final URL as JSON for AI agents.

ai-coding-security-pack.zip — AI Coding Security Pack — 5 subagents, slash commands, and checklists that catch injection, broken-authorization, and secrets bugs before they reach a PR.

Fetch one public HTTPS page and return bounded clean readable text, title, author, publish date, excerpt, word count, redirects, and final URL as JSON for AI agents.

Look up the current owner of one ERC-721 token on Base with ownerOf(uint256). Accepts a strict contract address and uint256 decimal token ID, performs one read-only eth_call with bounded public-RPC fallback, and returns the normalized owner address. Reverts, non-contracts, nonexistent tokens, malformed responses, and upstream failures return non-2xx and do not settle.

Create a bounded security evidence snapshot for a public HTTPS URL. Checks status, validated redirect chain, HSTS, CSP, X-Content-Type-Options, Referrer-Policy, Permissions-Policy, and cookie flags without retaining response-body content. Response metadata only; not a vulnerability scan or TLS-certificate audit.

Track what any Polymarket wallet is buying and selling — point your agent at a smart-money or whale address and get its public trades as a signal feed for copy-trading or market research, with no Polymarket account or API key. Reads the official account-free Polymarket Data API (data-api.polymarket.com/activity) for one strict 0x wallet address; optional bounded limit (default 25, max 100), offset (max 10,000), activity type, BUY/SELL side, start/end unix-second window, sortBy, and sortDirection. Returns sanitized activity rows — each with type, side, size, usdc_size, price, outcome, market title and slug, transaction hash, and unix timestamp — and drops name, pseudonym, bio, and profile images. Read-only; Fabler Labs is not affiliated with Polymarket; no betting execution, custody, or wager recommendation. Upstream failures, timeouts, oversized responses, and malformed or drifted schemas return non-2xx and do not settle.

Fetch one public HTTPS page and return bounded clean readable text, title, author, publish date, excerpt, word count, redirects, and final URL as JSON for AI agents.

Turn any public article or docs page into clean, LLM-ready text for RAG or summarization. Fetch one public HTTPS page and return bounded, readable text plus title, author, publish date, hostname, excerpt, word count, redirects, and final URL. HTML only; 8-second deadline; 512 KiB source and 50,000-character output limits.

Fact-check verdict written by Claude Haiku 5.5 (Anthropic) from real web sources: supported/contradicted/mixed/unverifiable, each source with its stance (supports/contradicts/neutral). Answer in a few seconds. Try GET /fact-check/sample. Independently monitored: lumierepaycheck.org/e?url=https://x402.agentindex.world/fact-check

Call it before you send, file or publish a document that quotes figures, names companies or cites papers. Post the text and every checkable claim comes back verified against dated primary sources, as one signed bundle with a per-claim receipt and its licence. Claims we cannot answer are named and never charged, and the preview is free. Verdicts: verified, stale, contradicted, unknown.

Call it before you send, file or publish a document that quotes figures, names companies or cites papers. Post the text and every checkable claim comes back verified against dated primary sources, as…