# Perplexity integrations: agent responses

> Create an agent response, create a chat completion and create embeddings in Perplexity. Connect Perplexity to the rest of your AI stack with Tray.ai.

**Canonical page:** https://tray.ai/connectors/perplexity-integrations/
**Categories:** AI
**Connects through:** HTTP Connector

## Overview

Perplexity is an AI answer engine whose API returns web-grounded answers with citations, raw web search results, embeddings and access to hosted models. Tray.ai connects to Perplexity through the HTTP Connector, so your workflows can call the Perplexity API alongside the rest of your stack.

## Use cases

### Agent responses

Read, create, and delete agent responses in Perplexity from any Tray.ai workflow. The Perplexity API covers calls such as create an agent response and get an agent response.

- Create an agent response
- Get an agent response
- Cancel an agent response

### Search and decisions

Read and manage search and decisions in Perplexity from any Tray.ai workflow. The Perplexity API covers calls such as search the web and answer typed questions.

- Search the web
- Answer typed questions

### Chat completions

Read and create chat completions in Perplexity from any Tray.ai workflow. The Perplexity API covers calls such as create a chat completion and list models.

- Create a chat completion
- List models

### Embeddings

Create embeddings in Perplexity from any Tray.ai workflow. The Perplexity API covers calls such as create embeddings and create contextualized embeddings.

- Create embeddings
- Create contextualized embeddings

### Skills

Read, create, and delete skills in Perplexity from any Tray.ai workflow. The Perplexity API covers calls such as list skills and create a skill.

- List skills
- Create a skill
- Get a skill

## Challenges Tray.ai solves

### Keeping Perplexity credentials out of logs

A raw API call usually means pasting a key or token into the request, where it ends up in step inputs, logs, and screenshots.

**How Tray.ai helps:** Store Perplexity credentials once as a Tray.ai authentication and reference them from the HTTP Connector. Tray.ai masks authentication values in logs, so the secret never shows up in a step's input or output.

### Going from the Perplexity API docs to a working call

Translating an example request from API docs into a workflow step means copying the method, URL, headers, and body by hand.

**How Tray.ai helps:** Paste a cURL example from the Perplexity API docs into the HTTP Connector and Tray.ai fills in the method, URL, headers, and body for you.

### Handling files and non-JSON responses

Not every API answers in JSON. Some return XML, files, or binary data, or expect a multipart upload.

**How Tray.ai helps:** The HTTP Connector parses JSON and XML responses, returns files you can pass to the next step, and sends multipart form data for uploads.

## Frequently asked questions

### Does Tray.ai connect to Perplexity?

Yes. Tray.ai connects to Perplexity through the HTTP Connector, which calls the Perplexity API directly. Any call the Perplexity API documents can run as a step in a Tray.ai workflow.

### How does Tray.ai authenticate with Perplexity?

The Perplexity API uses a bearer token. You save it once as a Tray.ai authentication, and the HTTP Connector adds it to every request.

### Can I get a dedicated Perplexity connector?

Perplexity runs through the HTTP Connector rather than a dedicated connector. If your team wants one, the Tray.ai connector SDK can build a dedicated Perplexity connector from the Perplexity API.

## Learn more

- Intelligent Integration: https://tray.ai/platform/intelligent-ipaas/
- Merlin Agent Builder: https://tray.ai/platform/merlin-agent-builder/
- Agent Gateway for MCP: https://tray.ai/platform/agent-gateway/
- Book a demo: https://tray.ai/contact/