Web Search Research x402 offerings

Extract the page's buttons as csv: fetches the URL, pulls every buttons 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 buttons as json: fetches the URL, pulls every buttons 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 buttons 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 buttons 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 buttons as markdown: fetches the URL, pulls every buttons 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 buttons as text: fetches the URL, pulls every buttons 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 Canada phone numbers from a web page: fetches the URL and returns numbers matching Canada's national/international formats (deduplicated, with an E.164 guess), so an agent gets callable contacts without parsing. $0.01 per page.

Bulk extract ca 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 page's canonical and alternates as csv: fetches the URL, pulls every canonical and alternates 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 canonical and alternates as json: fetches the URL, pulls every canonical and alternates 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 canonical and alternates 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 canonical and alternates as markdown: fetches the URL, pulls every canonical and alternates 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 canonical and alternates as text: fetches the URL, pulls every canonical and alternates 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 capitalized phrases from a web page: fetches the URL and returns every capitalized phrases 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 capitalized phrases 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 capitalized phrases 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 Switzerland phone numbers from a web page: fetches the URL and returns numbers matching Switzerland's national/international formats (deduplicated, with an E.164 guess), so an agent gets callable contacts without parsing. $0.01 per page.

Bulk extract ch 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.

Structured extraction preset for changelog entries 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 changelog entries: 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 changelog entries: 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 classes as csv: fetches the URL, pulls every classes 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 classes as json: fetches the URL, pulls every classes 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 classes 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.