Parallel: Run Task

Deep research for hard-to-find signals.

Tool ID: parallel_run_task

Run this action

Use the TypeScript SDK for a single call. Put ctx.tools.execute(...) inside a Play when the call should be durable, scheduled, or run across a CSV.

import { Deepline } from 'deepline';

const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
  'parallel_run_task',
  {
    "input": "example"
  },
);

console.log(result.toolResponse.raw);

CLI

deepline tools execute parallel_run_task --input '{
  "input": "example"
}' --json

Example response

The static output schema is not detailed enough to generate a reliable example. Use deepline tools get parallel_run_task --json for the complete live contract.

Input reference

Parallel run task input.

Name	Type	Required	Default	Details
`payload.processor`	`"lite" \| "lite-fast" \| "base" \| "base-fast" \| "core" \| "core-fast" \| "core2x" \| "core2x-fast" \| "pro" \| "pro-fast" \| "ultra" \| "ultra-fast" \| "ultra2x" \| "ultra2x-fast" \| "ultra4x" \| "ultra4x-fast" \| "ultra8x" \| "ultra8x-fast"`	No	`"lite-fast"`	Parallel processor tier (fast-only). Fast processors prioritize speed (2-5x faster) while maintaining very fresh data. Allowed: `lite`, `lite-fast`, `base`, `base-fast`, `core`, `core-fast`, `core2x`, `core2x-fast`, `pro`, `pro-fast`, `ultra`, `ultra-fast`, `ultra2x`, `ultra2x-fast`, `ultra4x`, `ultra4x-fast`, `ultra8x`, `ultra8x-fast`.
`payload.input`	`string \| record`	Yes	—	Required. Prompt or structured input for the task.
`payload.metadata`	`record`	No	—	—
`payload.source_policy`	`object`	No	—	Parallel source policy.
`payload.task_spec`	`object`	No	—	Parallel task spec.
`payload.mcp_servers`	`array`	No	—	—
`payload.enable_events`	`boolean`	No	—	—
`payload.webhook`	`object`	No	—	Parallel webhook.
`payload.betas`	`string \| array`	No	—	—
`payload.timeout`	`integer`	No	—	—

Output reference

Parallel task run result.

Name	Type	Required	Default	Details
`result.data`	`object`	Yes	—	Provider response payload.
`result.data.run`	`record`	No	—	—
`result.data.output`	`record`	No	—	—
`result.meta`	`record`	No	—	Additional response metadata (status, paging).

Deepline cost

Pricing model: provider_usage (provider usage).
Estimated Deepline credits: 0 per pricing unit.

Get started

Build and automate

Common workflows

Data and integrations

Reference

Parallel: Run Task

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

​Run this action

​CLI

​Example response

​Input reference

​Output reference

​Deepline cost

​Related documentation

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

Related documentation