Start free
ActionPerplexityUpdated June 2026

How do I run a long Perplexity Deep Research query?

Short answer: You can async chat (deep research) in Perplexity by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Perplexity Async Chat (Deep Research) action to a workflow, map its 3 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.

Async Chat (Deep Research) in Perplexity — start free All 3 Perplexity actions
Async Chat (Deep Research) in Perplexity — start free
Inputs

The fields this action accepts.

Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.

FieldTypeRequiredDescription
Model
model
optionsRequiredModel. Options: Sonar Deep Research, Sonar Reasoning Pro
Question
message
stringRequiredProvide a comprehensive analysis of recent advances in quantum computing for cryptography
System Prompt
system_prompt
stringOptionalSystem Prompt
Sample request
{
  "model": "{{trigger.model}}",
  "message": "Provide a comprehensive analysis of recent advances in quantum computing for cryptography",
  "system_prompt": "{{trigger.system_prompt}}"
}
Returns
{
  "id": "req_abc",
  "model": "sonar-deep-research",
  "status": "CREATED",
  "created_at": 1700000000
}

Use these fields in downstream nodes for routing, logging, or error handling.

Triggered by

Apps that pair well as the trigger for Async Chat (Deep Research).

Any of these apps can fire this action as part of a workflow.

Gmail → Perplexity
1 Gmail triggers
Slack → Perplexity
13 Slack triggers
Google Sheets → Perplexity
2 Google Sheets triggers
HubSpot → Perplexity
18 HubSpot triggers
FAQ

Questions about Async Chat (Deep Research).

What does the Async Chat (Deep Research) action do in Perplexity?
Submits a long-running research query asynchronously (e.g. with sonar-deep-research), returning a request_id. Poll Get Async Result for status and the final cited response.
What inputs does Async Chat (Deep Research) require?
Required: Model, Question. Every input accepts a static value or a variable from any upstream node in your workflow.
Can I use dynamic inputs from earlier workflow nodes?
Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.
What happens if Perplexity returns an error?
The workflow pauses on the failed node, the error message is captured in the run log, and you can retry the run with one click. Auto-retry policies are configurable per workflow with exponential backoff up to 5 attempts.
Does Async Chat (Deep Research) support batch operations?
Yes. Run Async Chat (Deep Research) inside a Loop node to process arrays. TinyCommand handles Perplexity's rate limits automatically so you don't have to throttle manually.
More actions

Other Perplexity actions.

Action
Chat Completion
Asks Perplexity (Sonar models) a question and gets a response grounded in fresh web results with explicit source citations. The go-to LLM API for "answer + citations" use cases.
Action
Get Async Result
Polls an async Perplexity request by ID and returns its status plus, once complete, the final response with citations. Standard pattern is to loop this every 10 to 30 seconds.
Async Chat (Deep Research) in Perplexity — start free