Skip to main content

​
Overview

n8n ships a native Perplexity node with full API coverage — Chat Completions, Agent, Search, and Embeddings — all configurable from the visual canvas. Models load dynamically from the API, so the dropdown always reflects the latest options.
n8n is a node-based workflow automation platform. It supports both self-hosted and cloud deployments — all examples below work in either. If you’re self-hosting, make sure your instance can reach api.perplexity.ai outbound. Learn more at n8n.io.
The node supports four resources:
  • Chat Completion — Sonar models with built-in web search, citations, and search controls
  • Agent — Third-party models (OpenAI, Anthropic, Google, xAI) with tool-calling and structured output
  • Search — Raw ranked web results for your own processing
  • Embeddings — Vector generation for RAG and retrieval pipelines

​
Prerequisites

  • n8n 2.14.0+ (cloud at app.n8n.cloud or self-hosted)
  • A Perplexity API key

Get API Key

Generate your Perplexity API key from the console.

​
Credential Setup

1

Open Credentials

In n8n, go to Settings → Credentials → Add credential.
2

Select Perplexity

Search for Perplexity API and select it.
3

Add Your Key

Paste your API key and save. The node will reference this credential automatically.
Perplexity credential setup

​
Chat Completion

Use Sonar models with built-in web search. This is the most common starting point — send a question, get a grounded answer with citations. Add a Perplexity node, set Resource to Chat Completion, and choose a model:
ParameterDescription
Modelsonar, sonar-pro, sonar-reasoning-pro, or sonar-deep-research
User MessageThe question or prompt — supports n8n expressions like ={{ $json.question }}
Chat Completion node configuration

​
Search Controls

The node exposes Perplexity’s full search filtering in the Options section: Search controls and additional parameters

​
Extracting Citations

The response includes a citations array of source URLs. Use a Code node after the Perplexity node to format them: 
const response = $input.first().json;
const content = response.choices[0].message.content;
const citations = response.citations ?? [];

return [{
  answer: citations.length > 0
    ? `${content}\n\nSources:\n${citations.map((c, i) => `[${i + 1}] ${c}`).join('\n')}`
    : content,
  citations
}];

​
Agent

Use the Agent resource to route through third-party models (OpenAI, Anthropic, Google, xAI) with Perplexity’s web_search and fetch_url tools. Set Resource to Agent and configure:
ParameterDescription
ModelAny model from the dynamic dropdown (e.g. openai/gpt-5.4, anthropic/claude-sonnet-4-6)
InputYour prompt — supports n8n expressions
ToolsSelect web_search, fetch_url, or both
System InstructionsOptional system prompt for the agent
Response FormatOptional JSON schema for structured output
Agent resource configuration
Get raw ranked web results without LLM processing. Set Resource to Search:
ParameterDescription
QueryThe search query — supports n8n expressions
Recencyday, week, month, or year
Domain FilterLimit to specific domains
LanguageISO 639-1 language code
CountryTwo-letter country code
Each result includes title, url, snippet, and date. Search resource results

​
Embeddings

Generate vectors for RAG and retrieval pipelines. Set Resource to Embeddings:
ParameterDescription
Modelpplx-embed-v1-4b (2560 dims) or pplx-embed-v1-0.6b (1024 dims)
InputText to embed — supports n8n expressions
The node also supports contextual embeddings via POST /v1/contextualizedembeddings for document-chunk-aware vectors. Embeddings resource configuration

​
Error Handling

Use n8n’s Error Trigger workflow or the built-in Retry on Fail setting (node settings → Retry on Fail) to handle transient errors:
  • 429 Too Many Requests — add a Wait node with exponential backoff before retrying
  • 401 Unauthorized — verify your Perplexity API credential is saved correctly
  • 500 errors — enable Retry on Fail in the node settings

n8n Docs

Official n8n documentation

n8n Community

Templates, workflows, and community support

Perplexity API Reference

Full API reference

Sonar Models

Available models and capabilities