Parallel · Web Data

Parallel API / Create Task Run

Initiates a task run. Returns immediately with a run object in status 'queued'. Beta features can be enabled by setting the 'parallel-beta' header.

Private Gateway connection

Data below comes from the configured private Gateway. Provider activation remains governed by its evidence and policy gates.

unverifiedRequest shape unavailableUnverified

Published API evidence

Public metadata only. Response bodies, credentials, and internal review notes are never displayed.

No verification date is claimed. No response capture is claimed.

Request parameters

advanced_settings body · optional
Advanced search configuration for the task run.
enable_events body · optional
Controls tracking of task run execution progress. When set to true, progress events are recorded and can be accessed via the [Task Run events](https://docs.parallel.ai/api-reference) endpoint. When false, no progress events are tracked. 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).
input body · required
Input to the task, either text or a JSON object. Example: "What was the GDP of France in 2023?"
mcp_servers body · optional
Optional list of MCP servers to use for the run.
memory_scope_key body · optional
User-provided key identifying the memory scope to use. Omit to use personal memory, if available.
metadata body · optional
User-provided metadata stored with the run. Keys and values must be strings with a maximum length of 16 and 512 characters respectively.
previous_interaction_id body · optional
Interaction ID to use as context for this request.
processor body · required
Processor to use for the task. Example: "base"
source_policy body · optional
Optional source policy governing included and excluded domains and domain/path prefixes in web search results.
task_spec body · optional
Task specification. If unspecified, defaults to auto output schema.
webhook body · optional
Callback URL (webhook endpoint) that will receive an HTTP POST when the run completes. This feature is not available via the Python SDK.

Provider docs How to run it