How to beginner · 3 min read

How to use code interpreter with OpenAI

Q: How to use code interpreter with OpenAI

Use the OpenAI API with the gpt-4o-mini or similar model and enable the tools parameter to include the code_interpreter tool. Send your code or coding queries in messages, and the model will execute code and return results. Use the OpenAI Python SDK v1+ with your API key from os.environ.

Quick answer

Use the OpenAI API with the gpt-4o-mini or similar model and enable the tools parameter to include the code_interpreter tool. Send your code or coding queries in messages, and the model will execute code and return results. Use the OpenAI Python SDK v1+ with your API key from os.environ.

PREREQUISITES

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

Setup

Install the official OpenAI Python SDK 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

Step by step

Use the OpenAI Python SDK to call the chat.completions.create method with the tools parameter specifying the code_interpreter tool. The model will run the code and return the output in the response.

python

import os
from openai import OpenAI

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

# Define the code interpreter tool
code_interpreter_tool = [{
    "type": "code_interpreter",
    "name": "code_interpreter"
}]

messages = [
    {"role": "user", "content": "Write a Python function to compute factorial of 5 and run it."}
]

response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=messages,
    tools=code_interpreter_tool
)

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

output

Model response:
The factorial of 5 is 120.

Common variations

You can use async calls with the OpenAI SDK, switch to other models like gpt-4o for more power, or stream responses for real-time output. The tools parameter must always include the code_interpreter tool to enable code execution.

python

import asyncio
import os
from openai import OpenAI

async def main():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    code_interpreter_tool = [{"type": "code_interpreter", "name": "code_interpreter"}]
    messages = [{"role": "user", "content": "Calculate the sum of squares from 1 to 10."}]

    # Async streaming example
    stream = await client.chat.completions.create(
        model="gpt-4o",
        messages=messages,
        tools=code_interpreter_tool,
        stream=True
    )

    print("Streaming output:")
    async for chunk in stream:
        delta = chunk.choices[0].delta.content or ""
        print(delta, end="", flush=True)

if __name__ == "__main__":
    asyncio.run(main())

output

Streaming output:
The sum of squares from 1 to 10 is 385.

Troubleshooting

If you get an error about missing tools, ensure you include the tools parameter with the code_interpreter tool in your API call.
If code execution is not working, verify your model supports code interpreter features (e.g., gpt-4o-mini or newer).
Check your API key environment variable is set correctly and the SDK version is 1.0 or higher.

✅

Key Takeaways

Use the OpenAI Python SDK v1+ with tools=[{"type": "code_interpreter", "name": "code_interpreter"}] to enable code execution.
The gpt-4o-mini model supports code interpreter; use more powerful models like gpt-4o for complex tasks.
Async and streaming calls are supported for real-time code execution output.
Always set your API key in os.environ["OPENAI_API_KEY"] and keep the SDK updated.
If code execution fails, verify tool inclusion and model compatibility.

Verified 2026-04 · gpt-4o-mini, gpt-4o

Verify ↗