Web Search Research x402 offerings

Bulk extract mailto 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.

Extract the page's main as csv: fetches the URL, pulls every main 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 main as json: fetches the URL, pulls every main 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.

Bulk extract main as json: 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 main 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 main as markdown: fetches the URL, pulls every main 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 main as text: fetches the URL, pulls every main 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 medium article 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 medium article: 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 medium article: 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 mentions from a web page: fetches the URL and returns every mentions 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 mentions 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 mentions 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 page's meta tags as csv: fetches the URL, pulls every meta tags 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 meta tags as json: fetches the URL, pulls every meta tags 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.

Bulk extract meta tags as json: 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 meta tags 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 meta tags as markdown: fetches the URL, pulls every meta tags 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 meta tags as text: fetches the URL, pulls every meta tags 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.

Extract money mentioned on a page: heuristic (pattern-based, no ML) recognition over the readable text, returning the distinct mentions with counts. Fast entity lists for tagging and triage; verify anything important. $0.01 per page.

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

Bulk extract mx 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.