- Integrations
- /
- Perplexity
- /
- Actions
- /
- Chat Completion
ActionPerplexityUpdated May 2026
How do I get a cited, web-grounded answer from Perplexity?
Short answer: Drop the "Perplexity → Chat Completion" action anywhere in your workflow, map the inputs from upstream nodes, and publish.
Inputs
The fields this action accepts.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Model model | options | Required | Model. Options: Sonar (default, with search), Sonar Pro (deeper search), Sonar Reasoning (complex queries) |
Message message | string | Required | Message. Example: What are the latest developments in quantum computing? |
System Prompt system_prompt | string | Optional | System Prompt. Example: Be precise and cite your sources. |
Temperature temperature | string | Optional | Temperature. Example: 0.2 |
Sample request
{"model": "{{trigger.model}}","message": "e.g. What are the latest developments in quantum computing?","system_prompt": "e.g. Be precise and cite your sources.","temperature": "e.g. 0.2"}
Returns
{"id": "abc123","model": "sonar","choices": [{"message": {"role": "assistant","content": "According to recent research..."},"finish_reason": "stop"}],"citations": ["https://example.com/article"]}
Use these fields in downstream nodes for routing, logging, or error handling.
Triggered by
Apps that pair well as the trigger for Chat Completion.
Any of these apps can fire this action as part of a workflow.
FAQ
Questions about Chat Completion.
What does the Chat Completion action do in Perplexity?
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.
What inputs does Chat Completion require?
Required: Model, Message. 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 Chat Completion support batch operations?
Yes. Run Chat Completion inside a Loop node to process arrays. Tiny Command handles Perplexity's rate limits automatically so you don't have to throttle manually.
More actions
Other Perplexity actions.
Action
Async Chat (Deep Research)
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.
ActionGet 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.
Send chat completion from your workflows.
Triggered by anything in the catalog. Free tier available. No credit card.