Browse published operations

Fetches text, highlights or summary for up to 100 URLs or Exa result ids in one call. Send urls or ids and pick text, highlights or summary. Priced per page, $0.001 per requested content type.

Search the web and generate a direct answer (or a cited summary) for a natural-language question, with citations. Flat $0.005/call estimate -- the settled charge is Exa's own reported cost (costDollars.total), not this estimate.

Find pages similar to a seed URL. DEPRECATED by Exa itself -- the spec recommends /search with a query describing the source instead. Priced as search: $0.007/call flat -- the settled charge is Exa's own reported cost (costDollars.total), not this estimate.

Neural or keyword web search. Send query; type (auto, fast, deep and others), numResults, category, domains and dates refine it, and contents adds page text. Returns ranked results with title, URL, date and highlights. The charge follows Exa's reported costDollars.

Complete a running Agent run early, returning the results gathered so far. You are billed for usage accrued before the stop. Currently supported only for max effort runs and requires the Exa-Beta: agent-max-effort-2026-07-27 header. If the run has already reached a terminal status, the API returns the existing run.

Creates a new Monitor to run recurring Exa searches on a schedule. Monitors automatically execute your search query on a recurring schedule and deliver results to your webhook endpoint with automatic deduplication: - Date-based filtering only fetches content since the last run - Semantic deduplication tracks previous outputs to surface only new developments The response includes a webhookSecret that is only returned once at creation time. Store it securely for webhook signature verification.

List stored events for an Agent run. Set Accept: text/event-stream to replay stored events as server-sent events. Use cursor for JSON pagination or Last-Event-ID for SSE replay.

Retrieve a single Agent run by ID.

Create an asynchronous Agent run. By default, the API returns the run object immediately. Set Accept: text/event-stream to stream run lifecycle events until the run reaches a terminal status.

Perform a batch action on monitors matching the provided filters. Supported actions: - delete: Permanently remove matching monitors - pause: Pause matching monitors - unpause: Unpause matching monitors Use dryrun: true (the default) to preview which monitors would be affected before performing the action. Results are paginated via the limit parameter; loop until hasmore is false to process all matching monitors.

Retrieves a single monitor by its ID.

Gets a specific monitor.

Creates a new Monitor to continuously keep your Websets updated with fresh data. Monitors automatically run on your defined schedule to ensure your Websets stay current without manual intervention: - Find new content: Execute search operations to discover fresh items matching your criteria - Update existing content: Run refresh operations to update items contents and enrichments - Automated scheduling: Configure cron expressions and timezone for precise scheduling control

Lists all runs for a monitor with cursor-based pagination. Runs are returned in reverse chronological order.

Retrieves a single run by its ID, including the full output if the run is completed.

Lists all runs for the Monitor.

Gets a specific monitor run.

Triggers a run immediately, regardless of the schedule. Works for monitors with status active or paused.