> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Parallel

> Parallel offers a Task API for automated, structured web research, transforming natural language queries into precise, schema-compliant outputs.

![Parallel logo](https://mintcdn.com/composio-preview/gqjBKmmJCINafaiK/images/toolkits/parallel.svg?fit=max\&auto=format\&n=gqjBKmmJCINafaiK\&q=85\&s=96d1fa9ee022b341b4e4e32300eb4345)

* **Category:** web search & research
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 42
* **Triggers:** 0
* **Slug:** `PARALLEL`
* **Version:** 20261101\_00
* **Instant:** Supported on the latest version. Support varies by tool.

## Tools

> [accordion] Add Enrichment to FindAll Run
>
> **Slug:** `PARALLEL_ADD_ENRICHMENT_TO_FIND_ALL_RUN`
>
> Tool to add an enrichment to a FindAll run. Use when you need to enrich existing FindAll run results with additional structured data fields. Enrichments define what information to extract from matched entities using a JSON schema.
>
> #### Input Parameters
>
> **processor** `string`
>
> Processor to use for the enrichment task. Defaults to 'core'.
>
> **findall\_id** `string` *required*
>
> ID of the FindAll run to add enrichment to.
>
> **mcp\_servers** `array`
>
> Optional list of MCP servers to use for the enrichment task.
>
> **output\_schema** `object` *required*
>
> JSON schema defining the structure and fields for the enrichment output.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Add Runs to Task Group
>
> **Slug:** `PARALLEL_ADD_RUNS_TO_TASK_GROUP`
>
> Tool to initiate multiple task runs within a TaskGroup. Use when you need to execute multiple tasks in parallel within an existing task group.
>
> #### Input Parameters
>
> **inputs** `array` *required*
>
> List of task runs to execute. Up to 1,000 runs can be specified per request.
>
> **taskgroup\_id** `string` *required*
>
> Unique identifier of the task group to add runs to.
>
> **default\_task\_spec** `object`
>
> Task specification for defining input and output schemas.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Cancel FindAll Run
>
> **Slug:** `PARALLEL_CANCEL_FIND_ALL_RUN`
>
> Tool to cancel an active FindAll run by findall\_id. Use when you need to stop a running FindAll operation before it completes. Cannot cancel runs that have already terminated.
>
> #### Input Parameters
>
> **findall\_id** `string` *required*
>
> ID of the FindAll run to cancel.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Chat Completions
>
> **Slug:** `PARALLEL_CREATE_CHAT_COMPLETIONS`
>
> Tool to get realtime chat completions from Parallel AI. Use when you need conversational AI responses or structured outputs via chat interface. Can be combined with Task API processors for research-grade structured outputs with citations and reasoning.
>
> #### Input Parameters
>
> **n** `integer`
>
> The number of chat completions to generate. Note: This parameter is currently unsupported by the API.
>
> **model** `string` *required*
>
> The model to use for chat completions. Available models: 'speed' (low latency), 'lite', 'base', 'core' (research-grade outputs).
>
> **top\_p** `number`
>
> The top p to use for chat completions. Note: This parameter is currently unsupported by the API.
>
> **stream** `boolean`
>
> Whether to stream the chat completions. When true, returns a stream of partial responses.
>
> **messages** `array` *required*
>
> The messages to use for chat completions. Must contain at least one message.
>
> **max\_tokens** `integer`
>
> The maximum number of tokens to generate. Note: This parameter is currently unsupported by the API.
>
> **temperature** `number`
>
> The temperature to use for chat completions. Note: This parameter is currently unsupported by the API.
>
> **response\_format** `object`
>
> Response format configuration for chat completions.
>
> **presence\_penalty** `number`
>
> The presence penalty to use for chat completions. Note: This parameter is currently unsupported by the API.
>
> **frequency\_penalty** `number`
>
> The frequency penalty to use for chat completions. Note: This parameter is currently unsupported by the API.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Monitor
>
> **Slug:** `PARALLEL_CREATE_MONITOR`
>
> Tool to create a web monitor that periodically runs the specified query. The monitor runs once at creation and then continues according to the specified cadence (hourly, daily, weekly, or every two weeks). Use when you need to track changes or developments for a specific search query over time.
>
> #### Input Parameters
>
> **query** `string` *required*
>
> Search query to monitor for material changes.
>
> **cadence** `string ("daily" | "weekly" | "hourly" | "every_two_weeks")` *required*
>
> Frequency at which the monitor runs: hourly, daily, weekly, or every\_two\_weeks.
>
> **webhook** `object`
>
> Webhook configuration for monitor notifications.
>
> **metadata** `object`
>
> User-provided metadata stored with the monitor. This field is returned in webhook notifications and GET requests, enabling you to map responses to corresponding objects in your application. For example, if you are building a Slackbot that monitors changes, you could store the Slack thread ID here to properly route webhook responses back to the correct conversation thread.
>
> **output\_schema** `object`
>
> Output schema configuration for monitor events.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Task Group
>
> **Slug:** `PARALLEL_CREATE_TASK_GROUP`
>
> Tool to create a new task group. Use when batching multiple tasks for parallel execution. Task Groups enable grouping and tracking of multiple task runs within a single manageable unit.
>
> #### Input Parameters
>
> **metadata** `object`
>
> User-provided metadata stored with the task group. Keys are strings, values can be string, integer, number, or boolean.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Create Task Run
>
> **Slug:** `PARALLEL_CREATE_TASK_RUN`
>
> Tool to create and initiate a task run. Returns immediately with a run object in status 'queued'. Use when you need to execute tasks asynchronously with Parallel AI processors.
>
> #### Input Parameters
>
> **input** `string` *required*
>
> Input to the task, either text or a JSON object.
>
> **webhook** `object`
>
> Webhook configuration for task run completion events.
>
> **metadata** `object`
>
> User-provided metadata stored with the run. Keys and values must be strings with a maximum length of 16 and 512 characters respectively.
>
> **processor** `string` *required*
>
> Processor to use for the task (e.g., 'lite', 'base', 'core', 'pro').
>
> **task\_spec** `object`
>
> Task specification defining input and output schemas.
>
> **mcp\_servers** `array`
>
> Optional list of MCP servers to use for the run. To enable this feature, specify 'mcp-server-2025-07-17' in the 'parallel-beta' header.
>
> **enable\_events** `boolean`
>
> Controls tracking of task run execution progress. When set to true, progress events are recorded and can be accessed via the Task Run events endpoint. Note that progress tracking cannot be enabled after a run has been created. The flag is set to true by default for premium processors (pro and above). To enable this feature, specify 'events-sse-2025-07-24' in the 'parallel-beta' header.
>
> **parallel\_beta** `string`
>
> Beta features to enable. Comma-separated list of beta feature flags (e.g., 'webhook-2025-08-12,events-sse-2025-07-24'). This will be sent as a header.
>
> **source\_policy** `object`
>
> Source policy governing preferred and disallowed domains in web search results.
>
> **previous\_interaction\_id** `string`
>
> Interaction ID to use as context for this request.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Delete Monitor
>
> **Slug:** `PARALLEL_DELETE_MONITOR`
>
> Tool to delete a monitor, stopping all future executions. Use when you need to permanently remove a monitor. Deleted monitors can no longer be updated or retrieved.
>
> #### Input Parameters
>
> **monitor\_id** `string` *required*
>
> Unique identifier of the monitor to delete. Deleted monitors can no longer be updated or retrieved.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Extend FindAll Run
>
> **Slug:** `PARALLEL_EXTEND_FIND_ALL_RUN`
>
> Tool to extend a FindAll run by adding additional matches to the current match limit. Use when you need to increase the number of matches for an existing FindAll run that is still active or has completed.
>
> #### Input Parameters
>
> **findall\_id** `string` *required*
>
> ID of the FindAll run to extend.
>
> **additional\_match\_limit** `integer` *required*
>
> Additional number of matches to find for this FindAll run. This value will be added to the current match limit to determine the new total match limit. Must be greater than 0.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Extract Content from URLs
>
> **Slug:** `PARALLEL_EXTRACT`
>
> Tool to extract relevant content from specific web URLs. Use when you need to fetch and extract content from known URLs with optional focusing on specific objectives or search queries.
>
> #### Input Parameters
>
> **urls** `array` *required*
>
> List of URLs to extract content from
>
> **excerpts** `string`
>
> Include excerpts from each URL relevant to the search objective and queries. Can be a boolean or settings object. Note that if neither objective nor search\_queries is provided, excerpts are redundant with full content.
>
> **objective** `string`
>
> If provided, focuses extracted content on the specified search objective
>
> **fetch\_policy** `object`
>
> Fetch policy configuration for cache and timeout settings.
>
> **full\_content** `string`
>
> Include full content from each URL. Can be a boolean or settings object. Note that if neither objective nor search\_queries is provided, excerpts are redundant with full content.
>
> **search\_queries** `array`
>
> If provided, focuses extracted content on the specified keyword search queries
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Extract Web Content
>
> **Slug:** `PARALLEL_EXTRACT_WEB_CONTENT`
>
> Extract excerpts or full content from known web URLs with Parallel's current stable Extract API. Prefer this action over PARALLEL\_EXTRACT, which uses the legacy beta API. The call is synchronous, so no polling is needed. Extraction costs \$1 per 1,000 URLs, with at most 20 URLs per request. Typical latency is 1 to 20 seconds. The default limit is 600 POST requests per minute, and Parallel documents no provider concurrency ceiling.
>
> #### Input Parameters
>
> **urls** `array` *required*
>
> URLs to extract content from. A request accepts at most 20 URLs.
>
> **objective** `string`
>
> Natural-language question or goal used with search\_queries to focus excerpts on relevant content.
>
> **session\_id** `string`
>
> Session identifier shared across related search and extract calls for improved context.
>
> **client\_model** `string`
>
> Model generating this request and consuming results, used to tailor defaults and optimizations.
>
> **search\_queries** `array`
>
> Keyword queries used with objective to focus excerpts on relevant content.
>
> **max\_chars\_total** `integer`
>
> Upper bound on total excerpt characters across all extracted results.
>
> **advanced\_settings** `object`
>
> Advanced extraction configuration that may affect quality and latency.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Fetch Task Group Runs
>
> **Slug:** `PARALLEL_FETCH_TASK_GROUP_RUNS`
>
> Fetch Task Group run events from a resumable stream, optionally filtering by status and including inputs and outputs. Events are collected and returned after the stream ends; use an event ID as a cursor to resume.
>
> #### Input Parameters
>
> **status** `string`
>
> Filter runs by status (e.g., queued, running, completed, failed, cancelled).
>
> **taskgroup\_id** `string` *required*
>
> Unique identifier of the Task Group to fetch runs from.
>
> **include\_input** `boolean`
>
> Whether to include task run inputs in the response. Default is False.
>
> **last\_event\_id** `string`
>
> ID of the last received event to resume streaming from. Used as cursor for pagination.
>
> **include\_output** `boolean`
>
> Whether to include task run outputs in the response. Default is False.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Start FindAll Run
>
> **Slug:** `PARALLEL_FIND_ALL`
>
> Tool to start a FindAll run. Use when you need to discover and match entities based on natural-language objectives. Supports custom conditions, exclusion lists, and webhook callbacks.
>
> #### Input Parameters
>
> **webhook** `object`
>
> Optional webhook configuration for run events.
>
> **metadata** `object`
>
> Optional user metadata to store with the run. Values must be primitive types (string, int, float, or bool).
>
> **generator** `string ("base" | "core" | "pro" | "preview")` *required*
>
> Quality/cost tier for the run.
>
> **objective** `string` *required*
>
> Natural-language objective for the FindAll run.
>
> **entity\_type** `string` *required*
>
> Type of entity to find (e.g., companies, people).
>
> **match\_limit** `integer` *required*
>
> Maximum number of matches to return (between 5 and 1000 inclusive).
>
> **exclude\_list** `array`
>
> Optional list of entities to exclude from matching.
>
> **match\_conditions** `array` *required*
>
> List of conditions that a candidate must satisfy.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Generate Grounded Response
>
> **Slug:** `PARALLEL_GENERATE_GROUNDED_RESPONSE`
>
> Generate a synchronous answer grounded in live web research with URL citation annotations. Successful requests cost \$10, \$50, or \$250 per 1,000 responses at low, medium, or high reasoning effort. Approximate completion times are 5-10, 15-20, or 30-60 seconds respectively. The result is returned synchronously in one call; no polling is required. Provider default rate and concurrency ceilings are not documented.
>
> #### Input Parameters
>
> **text** `object`
>
> Text and structured-output configuration.
>
> **input** `string` *required*
>
> A non-empty prompt string or role/content message list containing at least one user message.
>
> **model** `string`
>
> Model to run. Parallel is the only supported model.
>
> **metadata** `object`
>
> Up to 16 request tags. Keys may be up to 64 characters and values up to 512 characters.
>
> **reasoning** `object`
>
> Research effort configuration.
>
> **instructions** `string`
>
> System instructions for the model.
>
> **previous\_response\_id** `string`
>
> Previous response ID to use as conversation context.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get FindAll Run Result
>
> **Slug:** `PARALLEL_GET_FIND_ALL_RUN_RESULT`
>
> Tool to fetch the final (or latest available) FindAll candidates and result payload for a run. Use when you need to retrieve matched/unmatched candidates after a FindAll run has progressed or completed.
>
> #### Input Parameters
>
> **findall\_id** `string` *required*
>
> The identifier for the FindAll run.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get FindAll Run Schema
>
> **Slug:** `PARALLEL_GET_FIND_ALL_RUN_SCHEMA`
>
> Tool to retrieve the schema configuration of a FindAll run by findall\_id. Use when you need to inspect the objective, entity type, match conditions, and other schema details for a previously created FindAll run.
>
> #### Input Parameters
>
> **findall\_id** `string` *required*
>
> The identifier for the FindAll run.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Monitor
>
> **Slug:** `PARALLEL_GET_MONITOR`
>
> Retrieve a monitor's configuration and runtime state by ID using Parallel's current stable Monitor API. Prefer this action over PARALLEL\_RETRIEVE\_MONITOR, which uses the legacy alpha API. Reads do not execute checks and therefore do not incur documented check pricing. Monitor executions cost \$3 per 1,000 checks with the lite processor or \$10 per 1,000 checks with the base processor. The general rate-limit page says GET reads do not count against creation limits and documents 300 requests per minute only for legacy monitor POSTs, so no current GET rate is asserted here. The provider documents no concurrency ceiling.
>
> #### Input Parameters
>
> **monitor\_id** `string` *required*
>
> Unique identifier of the monitor to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Get Task Group
>
> **Slug:** `PARALLEL_GET_TASK_GROUP`
>
> Retrieve a current stable-API snapshot of a Task Group's aggregate run counts and status. Prefer this action over PARALLEL\_RETRIEVE\_TASK\_GROUP, which uses the legacy beta API. If status.is\_active is true, call this action again later to observe terminal status. This GET creates no billable Task run; task runs themselves cost by processor from \$5-\$2400 per 1,000 successful runs. The general rate-limit page says GET status/result reads do not count against the creation quota, while the task lifecycle page separately states 2,000 requests/minute across all Task calls. No provider concurrency ceiling is documented.
>
> #### Input Parameters
>
> **taskgroup\_id** `string` *required*
>
> Unique identifier of the task group to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Ingest FindAll Run
>
> **Slug:** `PARALLEL_INGEST_FIND_ALL_RUN`
>
> Tool to transform a natural language search objective into a structured FindAll specification. Use when you need to generate a FindAll run spec from a user's natural language description. The generated specification serves as a suggested starting point and can be further customized.
>
> #### Input Parameters
>
> **objective** `string` *required*
>
> Natural language search objective to transform into a structured FindAll specification. Describe what you want to find (e.g., 'Find technology companies in San Francisco with over 100 employees').
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Current Monitors
>
> **Slug:** `PARALLEL_LIST_CURRENT_MONITORS`
>
> List monitors from Parallel's current stable Monitor API, newest first, with optional type and status filters. Prefer this action over PARALLEL\_LIST\_MONITORS, which uses the legacy alpha API. Reads do not execute checks and therefore do not incur documented check pricing. Monitor executions cost \$3 per 1,000 checks with the lite processor or \$10 per 1,000 checks with the base processor. This operation is cursor-paginated; callers poll by passing next\_cursor as cursor only when another page is needed. The general rate-limit page says GET reads do not count against creation limits and documents 300 requests per minute only for legacy monitor POSTs, so no current GET rate is asserted here. The provider documents no concurrency ceiling.
>
> #### Input Parameters
>
> **type** `array`
>
> Monitor types to include. Each value is sent as a repeated type filter; omit for all types.
>
> **limit** `integer`
>
> Maximum monitors to return, from 1 through 10000. Defaults to 100.
>
> **cursor** `string`
>
> Opaque pagination token from next\_cursor. Omit for the first page.
>
> **status** `array`
>
> Monitor statuses to include. Each value is sent as a repeated status filter; defaults to active only.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Monitor Events
>
> **Slug:** `PARALLEL_LIST_MONITOR_EVENTS`
>
> Tool to list events for a monitor from up to the last 300 event groups. Retrieves events including errors and material changes in reverse chronological order.
>
> #### Input Parameters
>
> **monitor\_id** `string` *required*
>
> Unique identifier of the monitor to retrieve events for.
>
> **lookback\_period** `string`
>
> Lookback period to fetch events from. Sample values: `10d`, `1w`. A minimum of 1 day is supported and with one day increments. Use `d` for days, `w` for weeks.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Monitors
>
> **Slug:** `PARALLEL_LIST_MONITORS`
>
> List monitors with their configuration and current state. Supports pagination using a monitor ID cursor and limit; results can include active and canceled monitors.
>
> #### Input Parameters
>
> **limit** `string`
>
> Maximum number of monitors to return. If not specified, returns all monitors.
>
> **monitor\_id** `string`
>
> Monitor ID to start listing after (cursor for pagination). Returns monitors starting with this ID in lexicographic order.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Task Group Runs
>
> **Slug:** `PARALLEL_LIST_TASK_GROUP_RUNS`
>
> Collect Task Group runs from the current stable API's resumable event stream, optionally including structured inputs and outputs. Prefer this action over PARALLEL\_FETCH\_TASK\_GROUP\_RUNS, which uses the legacy beta API. Collection is bounded to 90 seconds, 1,000 events, and 3 MB; when truncated is true, pass the returned last\_event\_id to resume. This GET creates no billable Task run; task runs themselves cost by processor from \$5-\$2400 per 1,000 successful runs. The general rate-limit page says GET status/result reads do not count against the creation quota, while the task lifecycle page separately states 2,000 requests/minute across all Task calls. No provider concurrency ceiling is documented.
>
> #### Input Parameters
>
> **status** `string ("queued" | "action_required" | "running" | "completed" | "failed" | "cancelling" | "cancelled")`
>
> Return only runs with this status.
>
> **taskgroup\_id** `string` *required*
>
> Unique identifier of the Task Group whose runs to list.
>
> **include\_input** `boolean`
>
> Whether each event should include the task run input.
>
> **last\_event\_id** `string`
>
> Event cursor after which to resume the stream.
>
> **include\_output** `boolean`
>
> Whether completed events should include task run output.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Task Run Events
>
> **Slug:** `PARALLEL_LIST_TASK_RUN_EVENTS`
>
> Collect progress and state events from a Task Run using the current stable API. Prefer this action over PARALLEL\_STREAM\_TASK\_RUN\_EVENTS, which uses the legacy beta API. Collection is bounded to 90 seconds, 1,000 events, and 3 MB and fails rather than returning an incomplete event history when a bound is reached. This GET creates no billable Task run; task runs themselves cost by processor from \$5-\$2400 per 1,000 successful runs. The general rate-limit page says GET status/result reads do not count against the creation quota, while the task lifecycle page separately states 2,000 requests/minute across all Task calls. No provider concurrency ceiling is documented.
>
> #### Input Parameters
>
> **run\_id** `string` *required*
>
> Unique identifier of the Task Run whose events to list.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Make Decisions
>
> **Slug:** `PARALLEL_MAKE_DECISIONS`
>
> Answer 1-100 named predicate, choice, or score questions from shared state using current web evidence. Returns typed answers, including successful per-question refusals, plus request-level citations and usage.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.001 per fast request with up to 100 questions
>
> #### Input Parameters
>
> **mode** `string`
>
> Decision execution mode. Omit to use the provider's fast default.
>
> **state** `string` *required*
>
> Shared context used to answer every question. State plus the largest rendered question may use at most 32,000 provider-estimated input tokens.
>
> **questions** `object` *required*
>
> Map of 1-100 question names to typed questions. Names may contain only letters, digits, underscores, and hyphens; each rendered question is limited to 5,000 characters.
>
> **include\_excerpts** `boolean`
>
> Whether citations include supporting excerpts. When false, citation URLs and available titles remain but excerpts are empty.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Retrieve Event Group
>
> **Slug:** `PARALLEL_RETRIEVE_EVENT_GROUP`
>
> Tool to retrieve an event group for a monitor. Use when you have a valid monitor ID and event group ID and want to view the execution history.
>
> #### Input Parameters
>
> **monitor\_id** `string` *required*
>
> Unique identifier of the monitor.
>
> **event\_group\_id** `string` *required*
>
> Unique identifier of the event group to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Retrieve FindAll Run Status
>
> **Slug:** `PARALLEL_RETRIEVE_FIND_ALL_RUN_STATUS`
>
> Tool to retrieve status and metadata for a FindAll run by findall\_id. Use when you need to poll or check the progress of a FindAll run that was previously created.
>
> #### Input Parameters
>
> **findall\_id** `string` *required*
>
> ID of the FindAll run to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Retrieve Memory
>
> **Slug:** `PARALLEL_RETRIEVE_MEMORY`
>
> Retrieve relevant memories ranked against a query, or recent memories when the query is empty or omitted. The provider documents no operation-specific pricing, default rate limit, or concurrency limit. Retrieval is synchronous and returns in one call; no polling is required.
>
> #### Input Parameters
>
> **kind** `string ("task" | "monitor" | "findall")`
>
> Optional memory kind to return.
>
> **limit** `integer`
>
> Maximum number of memories to return.
>
> **query** `string`
>
> Concise query used to rank memories by relevance. Omit or pass an empty string to return the most recent memories.
>
> **since** `string`
>
> Only return memories from runs completed at or after this RFC 3339 timestamp.
>
> **memory\_scope\_key** `string`
>
> Memory scope key containing only letters, numbers, underscores, or hyphens. Required when the connection uses an app API key; omit only when personal memory is available.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Retrieve Monitor
>
> **Slug:** `PARALLEL_RETRIEVE_MONITOR`
>
> Tool to retrieve a specific monitor by ID. Returns the monitor configuration including status, cadence, query, and webhook settings.
>
> #### Input Parameters
>
> **monitor\_id** `string` *required*
>
> Unique identifier of the monitor to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Retrieve Task Group
>
> **Slug:** `PARALLEL_RETRIEVE_TASK_GROUP`
>
> Tool to retrieve details of a specific task group. Use when you have a valid task group ID and want to view its details.
>
> #### Input Parameters
>
> **taskgroup\_id** `string` *required*
>
> Unique identifier of the task group to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Retrieve Task Group Run
>
> **Slug:** `PARALLEL_RETRIEVE_TASK_GROUP_RUN`
>
> Tool to retrieve run status by run\_id for a task group. Use when you need to check the status of a specific task group run or poll for completion.
>
> #### Input Parameters
>
> **run\_id** `string` *required*
>
> Unique identifier of the run to retrieve.
>
> **taskgroup\_id** `string` *required*
>
> Unique identifier of the task group.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Retrieve Task Run
>
> **Slug:** `PARALLEL_RETRIEVE_TASK_RUN`
>
> Tool to retrieve run status by run\_id. Use when you need to check the status or details of a specific task run. The run result is available from the /result endpoint.
>
> #### Input Parameters
>
> **run\_id** `string` *required*
>
> ID of the task run to retrieve.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Retrieve Task Run Input
>
> **Slug:** `PARALLEL_RETRIEVE_TASK_RUN_INPUT`
>
> Tool to retrieve the input data of a specific task run by run\_id. Use when you need to view the original input parameters that were provided to a task run.
>
> #### Input Parameters
>
> **run\_id** `string` *required*
>
> Unique identifier of the task run to retrieve input for.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Retrieve Task Run Result
>
> **Slug:** `PARALLEL_RETRIEVE_TASK_RUN_RESULT`
>
> Tool to retrieve the result of a task run by run\_id, blocking until the run completes. Use when you need to wait for and fetch the final output of a previously initiated task run. The request will block until the run completes or the timeout is reached.
>
> #### Input Parameters
>
> **run\_id** `string` *required*
>
> The identifier of the task run to retrieve results for.
>
> **timeout** `integer`
>
> Timeout in seconds for blocking request. If not provided, defaults to 600 seconds (10 minutes). The request will block until the run completes or the timeout is reached.
>
> **parallel\_beta** `string`
>
> Optional beta version header for accessing beta features.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Parallel Search
>
> **Slug:** `PARALLEL_SEARCH`
>
> Tool to perform parallel semantic search. Use when you need to retrieve top matching documents for multiple queries in a single call.
>
> #### Input Parameters
>
> **search\_queries** `array` *required*
>
> List of search query texts to run in parallel Must be non-empty; all entries must be strings.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Search Web
>
> **Slug:** `PARALLEL_SEARCH_WEB`
>
> Search the web with Parallel's current stable Search API and return ranked results with markdown excerpts. Prefer this action over PARALLEL\_SEARCH, which uses the legacy beta API. The call is synchronous, so no polling is needed. Some connections allow only Fast mode with up to 10 results. Turbo and Fast cost \$1 per 1,000 requests. Basic and Advanced cost \$5 per 1,000 requests. Every mode includes 10 results, with extra results at \$1 per 1,000. Typical latency is 200 ms to 3 seconds. The default limit is 600 POST requests per minute, and Parallel documents no provider concurrency ceiling.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.001 per Fast search with up to 10 results
>
> **Discount:** 100
>
> #### Input Parameters
>
> **mode** `string ("turbo" | "fast" | "basic" | "advanced")`
>
> Supported web search quality and latency presets.
>
> **objective** `string`
>
> Self-contained natural-language question or goal used with search\_queries to focus relevance.
>
> **session\_id** `string`
>
> Session identifier shared across related search and extract calls for improved context.
>
> **client\_model** `string`
>
> Model generating this request and consuming results, used to tailor defaults and optimizations.
>
> **search\_queries** `array` *required*
>
> Concise keyword queries of 3-6 words each. At least one is required; provide 2-3 for best results.
>
> **max\_chars\_total** `integer`
>
> Upper bound on total excerpt characters across all results.
>
> **advanced\_settings** `object`
>
> Advanced web search configuration that may affect quality and latency.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Simulate Event
>
> **Slug:** `PARALLEL_SIMULATE_EVENT`
>
> Tool to simulate sending an event for a monitor. Use when testing monitor webhooks or validating monitor configurations. Simulates sending an event of the specified type (defaults to monitor.event.detected).
>
> #### Input Parameters
>
> **event\_type** `string ("monitor.event.detected" | "monitor.execution.completed" | "monitor.execution.failed")`
>
> Event types that can be simulated for a monitor.
>
> **monitor\_id** `string` *required*
>
> Unique identifier of the monitor to simulate an event for.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Stream FindAll Events
>
> **Slug:** `PARALLEL_STREAM_FIND_ALL_EVENTS`
>
> Collect FindAll run events, including candidate discovery, matching progress and run status, and return them as a list after the event stream ends. Unrecognized event types are ignored.
>
> #### Input Parameters
>
> **timeout** `integer`
>
> Duration in seconds to keep the connection open if no new events occur.
>
> **findall\_id** `string` *required*
>
> Unique identifier of the FindAll run to stream events from.
>
> **last\_event\_id** `string`
>
> ID of the last received event to resume streaming from.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Stream Task Group Events
>
> **Slug:** `PARALLEL_STREAM_TASK_GROUP_EVENTS`
>
> Collect Task Group events, including group status and task run updates, and return them as a list after the event stream ends. Unrecognized event types are ignored.
>
> #### Input Parameters
>
> **timeout** `integer`
>
> Duration in seconds to keep the connection open if no new events occur.
>
> **taskgroup\_id** `string` *required*
>
> Unique identifier of the Task Group to stream events from.
>
> **last\_event\_id** `string`
>
> ID of the last received event to resume streaming from.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Stream Task Run Events
>
> **Slug:** `PARALLEL_STREAM_TASK_RUN_EVENTS`
>
> Collect Task Run events, including progress updates and state changes, and return them as a list after the event stream ends. Unrecognized event types are ignored.
>
> #### Input Parameters
>
> **run\_id** `string` *required*
>
> Unique identifier of the Task Run to stream events from.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Suggest Task
>
> **Slug:** `PARALLEL_SUGGEST_TASK`
>
> Tool to suggest tasks based on user intent. Use when you need task specifications generated from a natural language description of what you want to accomplish.
>
> #### Input Parameters
>
> **user\_intent** `string` *required*
>
> User intent to guide the suggestion (e.g., 'Build authentication system for web app')
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] Update Monitor
>
> **Slug:** `PARALLEL_UPDATE_MONITOR`
>
> Tool to update a monitor's configuration. Use when you need to modify an existing monitor's cadence, query, metadata, or webhook settings. At least one field must be non-null to apply an update.
>
> #### Input Parameters
>
> **query** `string`
>
> Updated search query for the monitor. Use this for minor updates to prompts and instructions only. Major changes to the query may lead to unexpected results in change detection, as the monitor compares new results with what was previously seen.
>
> **cadence** `string ("daily" | "weekly" | "hourly" | "every_two_weeks")`
>
> Monitor cadence options.
>
> **webhook** `object`
>
> Webhook configuration for monitor updates.
>
> **metadata** `object`
>
> Updated user-provided metadata. This field is returned in webhook notifications, enabling you to map responses to corresponding objects in your application.
>
> **monitor\_id** `string` *required*
>
> Unique identifier of the monitor to update.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
