Skip to main content

​
Overview

Perplexity’s Chat Completions API provides web-grounded AI responses with support for streaming, tools, search options, and more. You can use it with OpenAI-compatible client libraries or our native SDKs for type safety and enhanced features. Use the Chat Completions API when you need web search capabilities built-in, streaming responses, or Perplexity’s Sonar models. For structured outputs and third-party models, use our Agentic Research API.
Keep using your existing OpenAI SDKs to get started fast; switch to our native SDKs later as needed.

​
Installation

Install the SDK for your preferred language: 
pip install perplexityai

​
Authentication

Set your API key as an environment variable. The SDK will automatically read it: 
export PERPLEXITY_API_KEY="your_api_key_here"
Or use a .env file in your project:
.env
PERPLEXITY_API_KEY=your_api_key_here
All SDK examples below automatically use the PERPLEXITY_API_KEY environment variable. You can also pass the key explicitly if needed.

​
Generating an API Key

Get your Perplexity API Key

Navigate to the API Keys tab in the API Portal and generate a new key.
OpenAI SDK Compatible: Perplexity’s API supports the OpenAI Chat Completions format. You can use OpenAI client libraries by pointing to our endpoint.

​
Basic Usage

​
Non-Streaming Request

from perplexity import Perplexity

client = Perplexity()

completion = client.chat.completions.create(
    model="sonar-pro",
    messages=[
        {"role": "user", "content": "What were the results of the 2025 French Open Finals?"}
    ]
)

print(completion.choices[0].message.content)

​
Streaming Response

from perplexity import Perplexity

client = Perplexity()

stream = client.chat.completions.create(
    model="sonar-pro",
    messages=[
        {"role": "user", "content": "What are the most popular open-source alternatives to OpenAI's GPT models?"}
    ],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")
For a full guide on streaming, including parsing, error handling, citation management, and best practices, see our streaming guide.

​
Response Structure

Chat Completions responses follow the OpenAI-compatible format: 
{
    "id": "pplx-1234567890",
    "model": "sonar-pro",
    "created": 1234567890,
    "choices": [
        {
            "index": 0,
            "message": {
                "role": "assistant",
                "content": "The 2025 French Open Finals results..."
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "prompt_tokens": 12,
        "completion_tokens": 315,
        "total_tokens": 327
    }
}

​
Next Steps

Chat Completions Guide

Complete guide to the Chat Completions API with advanced features and examples.

Models

Explore available Sonar models and their capabilities.

API Reference

View complete endpoint documentation and parameters.

Search Controls

Learn how to control search behavior with filters and parameters.

Agentic Research API

Need structured outputs or third-party models? Check out the Agentic Research API.

Search API

Get raw search results with the Search API.
Need help? Check out our community for support and discussions with other developers.