---
title: "Perplexity AI integration for LuumenAI"
url: "https://www.luumen.ai/integrations/perplexity-ai/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# Perplexity AI integration for LuumenAI

Web-grounded answers and long-running research jobs from the terminal

## What LuumenAI can do with Perplexity AI

LuumenAI connects to Perplexity AI with an API token and exposes 9 tools (7 read-only · 2 write). For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

## Key facts

- Authentication: API token
- Tools available: 9 tools (7 read-only · 2 write)
- Deployment: scoped as part of your Pilot, Platform, or Managed rollout
- Category: AI & automation

## About Perplexity AI with LuumenAI

Connect Perplexity AI and the agent can search the web and ask Sonar models for sourced answers while it works a ticket. Useful for checking a CVE, reading a vendor advisory, or confirming an end-of-support date without leaving the terminal. Longer research runs as an async job you approve first, then collect when it finishes. Luumen authenticates with an API key.

## Example tools

Read-only (7 in total):

- `PERPLEXITYAI_CREATE_CHAT_COMPLETION` — Perplexity Sonar Chat Completions (POST /v1/sonar).
- `PERPLEXITYAI_CREATE_CONTEXTUALIZED_EMBEDDINGS` — Create Contextualized Embeddings (POST /v1/contextualizedembeddings).
- `PERPLEXITYAI_CREATE_EMBEDDINGS` — Generate vector embeddings for independent texts (queries, sentences, documents).
- `PERPLEXITYAI_GET_ASYNC_CHAT_COMPLETION` — Get Async Chat Completion (GET /v1/async/sonar/{id}).
- `PERPLEXITYAI_LIST_ASYNC_CHAT_COMPLETIONS` — List Async Chat Completions (GET /v1/async/sonar).
- `PERPLEXITYAI_LIST_MODELS` — List Models (GET /v1/models).
- `PERPLEXITYAI_SEARCH` — Search the Web (POST /search).

Write and destructive (2 in total, subject to configured approval policy):

- `PERPLEXITYAI_CREATE_ASYNC_CHAT_COMPLETION` — Create Async Chat Completion (POST /v1/async/sonar).
- `PERPLEXITYAI_EXECUTE_AGENT` — Create Agent Response (POST /v1/agent).

## Frequently asked questions

### How does LuumenAI connect to Perplexity AI?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in Perplexity AI on its own?

For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

### Is there an audit trail?

Every call to Perplexity AI — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/perplexity-ai/