How to beginner · 3 min read

Perplexity API for search

Q: Perplexity API for search

Use the OpenAI SDK with the perplexity-search model to perform search queries via the Perplexity API. Send your query as a chat message and parse the response for relevant search results.

Quick answer

Use the OpenAI SDK with the perplexity-search model to perform search queries via the Perplexity API. Send your query as a chat message and parse the response for relevant search results.

PREREQUISITES

Python 3.8+
OpenAI API key (free tier works)
pip install openai>=1.0

Setup

Install the official openai Python package and set your API key as an environment variable.

Run pip install openai to install the SDK.
Set your API key in your shell: export OPENAI_API_KEY='your_api_key' (Linux/macOS) or setx OPENAI_API_KEY "your_api_key" (Windows).

bash

pip install openai

output

Collecting openai
  Downloading openai-1.x.x-py3-none-any.whl (xx kB)
Installing collected packages: openai
Successfully installed openai-1.x.x

Step by step

Use the OpenAI client to call the Perplexity search model with a chat completion request. The example below sends a search query and prints the top result.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

messages = [
    {"role": "user", "content": "Search for the latest AI research papers on GPT models."}
]

response = client.chat.completions.create(
    model="perplexity-search",
    messages=messages
)

print("Search result:", response.choices[0].message.content)

output

Search result: Here are the latest AI research papers on GPT models: 1. "Scaling Laws for Neural Language Models" by OpenAI, 2. "GPT-4 Technical Report" by OpenAI, 3. "Improving Language Understanding with Retrieval-Augmented Generation" ...

Common variations

You can use async calls for better performance or stream results for real-time output. Also, you can switch to other search-related models if available.

python

import asyncio
import os
from openai import OpenAI

async def async_search():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    messages = [{"role": "user", "content": "Find recent breakthroughs in AI."}]
    
    # Async call
    response = await client.chat.completions.acreate(
        model="perplexity-search",
        messages=messages
    )
    print("Async search result:", response.choices[0].message.content)

asyncio.run(async_search())

output

Async search result: Recent breakthroughs in AI include advancements in large language models like GPT-4, improvements in multimodal AI, and new techniques in reinforcement learning.

Troubleshooting

If you get authentication errors, verify your OPENAI_API_KEY environment variable is set correctly.
If the model perplexity-search is not found, check your API access or use an alternative search model.
For rate limits, implement retries with exponential backoff.

✅

Key Takeaways

Use the OpenAI SDK with perplexity-search model for search queries.
Set your API key securely via environment variables before running code.
Async and streaming calls improve responsiveness for search applications.
Check model availability and API permissions if you encounter errors.

Verified 2026-04 · perplexity-search

Verify ↗