Web Search Research x402 offerings

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

Extract the utm tagged links from a page: fetches the URL, resolves every href and returns the ones that are utm tagged 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 utm tagged 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 utm tagged 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 uuids from a web page: fetches the URL and returns every uuids 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 uuids 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.

Change watch for extract uuids 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.

Extract vat numbers eu from a web page: fetches the URL and returns every vat numbers eu 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.

Extract version numbers from a web page: fetches the URL and returns every version numbers 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.

Change watch for extract version numbers 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.

Extract the video links from a page: fetches the URL, resolves every href and returns the ones that are video 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 video 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 video 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 the page's videos as csv: fetches the URL, pulls every videos element and returns them as CSV rows, with a count. Structured, one-element-type extraction for agents and pipelines; no browser needed. $0.01 per page.

Extract the page's videos as json: fetches the URL, pulls every videos element and returns them as a JSON array, with a count. Structured, one-element-type extraction for agents and pipelines; no browser needed. $0.01 per page.

Change watch for extract videos as json: 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 the page's videos as markdown: fetches the URL, pulls every videos element and returns them as a Markdown list, with a count. Structured, one-element-type extraction for agents and pipelines; no browser needed. $0.01 per page.

Extract the page's videos as text: fetches the URL, pulls every videos element and returns them as plain lines, with a count. Structured, one-element-type extraction for agents and pipelines; no browser needed. $0.01 per page.

Structured extraction preset for wikipedia infobox pages: fetches the URL and applies a layout-aware extractor (structured data first, then known markup patterns) to return clean fields instead of raw HTML. Layouts change, so results are best-effort and empty when the pattern no longer matches. $0.01 per page.

Bulk extract wikipedia infobox: 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 wikipedia infobox: 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 the wikipedia links from a page: fetches the URL, resolves every href and returns the ones that are wikipedia 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 wikipedia 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 wikipedia 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.