How to beginner · 3 min read

How to use ChatGPT plugins

Q: How to use ChatGPT plugins

To use ChatGPT plugins, first enable plugins in your ChatGPT settings and select the desired plugins from the plugin store. Then, interact with the model specifying plugin-enabled conversations via the API or ChatGPT interface to access extended capabilities.

Quick answer

To use ChatGPT plugins, first enable plugins in your ChatGPT settings and select the desired plugins from the plugin store. Then, interact with the model specifying plugin-enabled conversations via the API or ChatGPT interface to access extended capabilities.

PREREQUISITES

OpenAI account with ChatGPT Plus or Enterprise access
API key with plugin access enabled
Python 3.8+
pip install openai>=1.0

Setup

Enable plugins in your ChatGPT account settings under the "Beta features" section. Install the openai Python package with pip install openai. Set your API key as an environment variable OPENAI_API_KEY to authenticate requests.

bash

pip install openai>=1.0

Step by step

Use the OpenAI Python SDK to create a chat completion request with plugin-enabled messages. Specify the model that supports plugins (e.g., gpt-4o with plugins enabled) and include plugin calls in the conversation. Below is a minimal example to call a plugin-enabled ChatGPT session.

python

import os
from openai import OpenAI

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

messages = [
    {"role": "system", "content": "You are a helpful assistant with plugin access."},
    {"role": "user", "content": "Find me the latest news about AI."}
]

response = client.chat.completions.create(
    model="gpt-4o",
    messages=messages,
    plugins=["news-plugin"]  # Example plugin identifier
)

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

output

Latest AI news: [Plugin response with current headlines]

Common variations

You can use async calls with the OpenAI SDK for better performance or stream plugin responses for real-time output. Different models like gpt-4o or gemini-1.5-pro may support different plugins. Adjust the plugins parameter accordingly.

python

import asyncio
import os
from openai import OpenAI

async def main():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    messages = [
        {"role": "system", "content": "You are a helpful assistant with plugin access."},
        {"role": "user", "content": "Get weather updates for New York City."}
    ]
    response = await client.chat.completions.acreate(
        model="gpt-4o",
        messages=messages,
        plugins=["weather-plugin"]
    )
    print(response.choices[0].message.content)

asyncio.run(main())

output

Current weather in New York City: Sunny, 72°F

Troubleshooting

If you get an "Unauthorized" error, verify your API key and plugin access permissions.
If plugins do not respond, ensure they are enabled in your ChatGPT settings and the plugin ID is correct.
For rate limits, check your OpenAI usage dashboard and upgrade your plan if needed.

✅

Key Takeaways

Enable plugins in ChatGPT settings before using them via API or UI.
Use the OpenAI SDK with the correct model and plugin identifiers to call plugins.
Async and streaming calls improve responsiveness for plugin-enabled chats.
Check API key permissions and plugin enablement if you encounter errors.

Verified 2026-04 · gpt-4o, gemini-1.5-pro

Verify ↗