Exa

Performs a search based on the query and generates either a direct answer or a detailed summary with citations, depending on the query type.

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 `dry_run: true` (the default) to preview which monitors would be affected before performing the action. Results are paginated via the `limit` parameter; loop until `has_more` is `false` to process all matching monitors.

Cancel a queued or running Agent run. If the run has already reached a terminal status, the API returns the existing run.

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.

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.

Delete a stored Agent run.

Deletes a monitor. This cannot be undone.

Get a single Event by id. You can subscribe to Events by creating a Webhook.

List all events that have occurred in the system. You can paginate through the results using the `cursor` parameter.

Find links similar to the provided URL and optionally retrieve their contents. Deprecated: prefer `/search` with a query describing the source.

Retrieve a single Agent run by ID.

Contents

Retrieves a single monitor by its ID.

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

Creates a new import to upload your data into Websets. Imports can be used to: - **Enrich**: Enhance your data with additional information using our AI-powered enrichment engine - **Search**: Query your data using Websets' agentic search with natural language filters - **Exclude**: Prevent duplicate or already known results from appearing in your searches Once the import is created, you can upload your data to the returned `uploadUrl` until `uploadValidUntil` (by default 1 hour).

Deletes a import.

Gets a specific import.

Lists all imports for the Webset.

Updates a import configuration.

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.

List Agent runs for your team, ordered from newest to oldest.

Lists all monitors for the authenticated team. Supports filtering by status and cursor-based pagination.

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

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

Deletes a monitor.

Gets a specific monitor.

Lists all monitors for the Webset.

Gets a specific monitor run.

Lists all runs for the Monitor.

Updates a monitor configuration.

Create a new research request

Retrieve research by ID. Add ?stream=true for real-time SSE updates.

Get a paginated list of research requests

Perform a search with an Exa prompt-engineered query and retrieve a list of relevant results. Optionally get contents.

Returns information about the authenticated team, including current concurrency usage and limits.

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

Updates an existing monitor. All fields are optional. For `search`, you can send a partial object containing only the fields you want to change. Set `trigger` to `null` to remove the schedule.

List all attempts made by a Webhook ordered in descending order.

Create a Webhook

Delete a Webhook

Get a Webhook

List webhooks

Update a Webhook

Cancels all operations being performed on a Webset. Any enrichment or search will be stopped and the Webset will be marked as `idle`.

Creates a new Webset with optional search, import, and enrichment configurations. The Webset will automatically begin processing once created. You can specify an `externalId` to reference the Webset with your own identifiers for easier integration.

Deletes a Webset. Once deleted, the Webset and all its Items will no longer be available.

All running enrichments will be canceled. You can not resume an Enrichment after it has been canceled.

Create an Enrichment for a Webset.

When deleting an Enrichment, any running enrichments will be canceled and all existing `enrichment_result` generated by this Enrichment will no longer be available.

Get an Enrichment

Update an Enrichment configuration for a Webset.

Get a Webset

Deletes an Item from the Webset. This will cancel any enrichment process for it.

Returns a Webset Item.

Returns a list of Webset Items. You can paginate through the Items using the `cursor` parameter.

Returns a list of Websets. You can paginate through the results using the `cursor` parameter. You can filter results using the `search` parameter to find Websets by ID, external ID, or title.

Preview how a search query will be decomposed before creating a webset. This endpoint performs the same query analysis that happens during webset creation, allowing you to see the detected entity type, generated search criteria, and available enrichment columns in advance. Use this to help users understand how their search will be interpreted before committing to a full webset creation.

Cancels a currently running Search. You can cancel all searches at once by using the `websets/:webset/cancel` endpoint.

Creates a new Search for the Webset. The default behavior is to reuse the previous Search results and evaluate them against the new criteria.

Gets a Search by id

Update a Webset