How to Intermediate · 3 min read

How to enable code interpreter in OpenAI assistant

Quick answer

To enable the code interpreter in an OpenAI assistant, you must specify the functions parameter with a code execution function in your chat completion request using the OpenAI SDK. This allows the assistant to run code snippets securely during the conversation.

PREREQUISITES

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

Setup

Install the official openai Python SDK version 1.0 or higher and set your API key as an environment variable.

Install SDK: pip install openai>=1.0
Set environment variable: export OPENAI_API_KEY='your_api_key' (Linux/macOS) or setx OPENAI_API_KEY "your_api_key" (Windows)

bash

pip install openai>=1.0

Step by step

Use the OpenAI SDK to create a chat completion request that includes a functions parameter defining a code interpreter function. This enables the assistant to execute code snippets during the chat.

python

import os
from openai import OpenAI

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

# Define a function schema for code execution
functions = [
    {
        "name": "code_interpreter",
        "description": "Executes Python code snippets securely.",
        "parameters": {
            "type": "object",
            "properties": {
                "code": {
                    "type": "string",
                    "description": "Python code to execute"
                }
            },
            "required": ["code"]
        }
    }
]

messages = [
    {"role": "user", "content": "Calculate the factorial of 5 using Python code."}
]

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages,
    functions=functions,
    function_call="auto"  # Let the model decide when to call the function
)

print("Assistant response:")
print(response.choices[0].message.content)

# If the model calls the function, you would then execute the code securely on your side
# and send the result back to the model in a follow-up message (not shown here).

output

Assistant response:
{"function_call": {"name": "code_interpreter", "arguments": "{\"code\": \"import math\nfactorial = math.factorial(5)\nfactorial\"}"}}

Common variations

You can customize the code interpreter by changing the functions schema or use different models like gpt-4o-mini for faster responses. Async calls and streaming are also supported by the OpenAI SDK.

python

import asyncio
import os
from openai import OpenAI

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

async def async_code_interpreter():
    response = await client.chat.completions.acreate(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": "Run Python code to add 2 + 2."}],
        functions=[
            {
                "name": "code_interpreter",
                "description": "Executes Python code snippets.",
                "parameters": {
                    "type": "object",
                    "properties": {
                        "code": {"type": "string"}
                    },
                    "required": ["code"]
                }
            }
        ],
        function_call="auto"
    )
    print(response.choices[0].message.content)

asyncio.run(async_code_interpreter())

output

{"function_call": {"name": "code_interpreter", "arguments": "{\"code\": \"2 + 2\"}"}}

Troubleshooting

If the assistant does not execute code, ensure you have included the functions parameter with the correct schema.
Check that your API key is set correctly in os.environ["OPENAI_API_KEY"].
Function calling requires models that support it, like gpt-4o-mini or gpt-4o-mini.

✅

Key Takeaways

Use the functions parameter in client.chat.completions.create() to enable code interpreter functionality.
Define a clear function schema describing the code execution interface for the assistant.
Models like gpt-4o-mini support function calling required for code interpretation.
Always securely execute code on your backend after receiving the function call from the assistant.
Set your API key in environment variables and use the official openai SDK v1+.

Verified 2026-04 · gpt-4o-mini

Verify ↗