Web Search Research x402 offerings

Evaluate a claim or question against one supplied HTML or PDF source and return anchored evidence.

Retrieve deterministic evidence from a public HTTPS page

Inspect a business or project website for its published description, structured data and pricing, contact, documentation and social links. Reports source claims, not verified company facts.

Read a public static HTTPS webpage as clean text with headings, links, timestamp and content hash. Use to ground an answer or ingest documentation. Respects robots.txt; no JavaScript or login.

Extract published JSON-LD and optional CSS-selector fields from a public static HTTPS page. Use for product data, organization metadata or repeatable structured extraction. No inferred values.

Read up to three public static HTTPS webpages in one paid call for comparisons or multi-source context. All pages must succeed or the request is not settled.

Read a public static HTTPS webpage as clean text with headings, links, timestamp and content hash. Use to ground an answer or ingest documentation. Respects robots.txt; no JavaScript or login.

Answers factual research questions with AI-generated summaries and source citations, powered by Exa web search. Handles 'who is' questions about people and their roles — e.g. identifying who holds a specific title or position at a company (head of AI, CEO, CTO), looking up a person by role, and general fact-finding and research lookups.

Returns enriched content data from Exa for a given request.

Fetches content from web pages and documents using Exa.

Search the web and return relevant results for a query.

Search the web with Exa and return relevant results.

Search the web with Exa’s API and return relevant results for your queries.

Search the Exa marketplace for relevant results and listings.

Render any public web page in a real headless Chrome and return its text. JavaScript runs first, so single-page apps and docs sites that a plain fetch returns empty come back complete. Returns the title, description, headings, the full visible text and every outbound link. Pass ?url= and ?full=1. Free without payment: the title, description, headings and the first 400 characters, so you can tell whether it is the page you wanted before paying. Refuses private and reserved add

Bulk extract acronyms: 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 extract acronyms: 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.

Extract United Arab Emirates phone numbers from a web page: fetches the URL and returns numbers matching United Arab Emirates's national/international formats (deduplicated, with an E.164 guess), so an agent gets callable contacts without parsing. $0.01 per page.

Bulk extract ae phone numbers: 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.

Extract the affiliate links from a page: fetches the URL, resolves every href and returns the ones that are affiliate links with their anchor text, deduplicated, plus a count. One link category per call for crawlers, auditors and content agents. $0.01 per page.

Bulk extract affiliate links: 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 extract affiliate links: 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.

Extract all caps terms from a web page: fetches the URL and returns every all caps terms found in the page text and markup (deduplicated, with counts and up to 300 items), so an agent gets the values without parsing HTML. $0.01 per page.

Bulk extract all caps terms from page: 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.