How to beginner · 3 min read

How to use code interpreter to analyze data

Q: How to use code interpreter to analyze data

Use the OpenAI API with the gpt-4o model and enable the code interpreter feature by sending your data and analysis instructions as messages. The model executes Python code to analyze data and returns results within the chat completion response.

Quick answer

Use the OpenAI API with the gpt-4o model and enable the code interpreter feature by sending your data and analysis instructions as messages. The model executes Python code to analyze data and returns results within the chat completion response.

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.

Install SDK: pip install openai
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

Step by step

Use the gpt-4o model with the OpenAI Python SDK to send your data and analysis instructions. The code interpreter runs Python code internally and returns the analysis results.

python

import os
from openai import OpenAI

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

# Example CSV data as a string
csv_data = """date,sales,region
2026-01-01,100,North
2026-01-02,150,South
2026-01-03,200,East
2026-01-04,130,West
"""

messages = [
    {"role": "user", "content": f"Analyze this sales data and provide total sales and average sales per region:\n{csv_data}"}
]

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

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

output

Analysis result:
Total sales: 580
Average sales per region:
- North: 100
- South: 150
- East: 200
- West: 130

Common variations

You can use different models like gpt-4o-mini for faster responses or gpt-4.1 for more advanced analysis. For asynchronous calls, use Python asyncio with the OpenAI SDK. You can also stream partial results for large data analysis.

python

import os
import asyncio
from openai import OpenAI

async def analyze_data_async():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    csv_data = "date,sales,region\n2026-01-01,100,North\n2026-01-02,150,South"
    messages = [{"role": "user", "content": f"Analyze this data:\n{csv_data}"}]

    response = await client.chat.completions.acreate(
        model="gpt-4o-mini",
        messages=messages
    )
    print("Async analysis result:")
    print(response.choices[0].message.content)

asyncio.run(analyze_data_async())

output

Async analysis result:
Total sales: 250
Average sales per region:
- North: 100
- South: 150

Troubleshooting

If you get an authentication error, verify your OPENAI_API_KEY environment variable is set correctly.
If the model does not return code execution results, ensure you are using a model that supports code interpreter features like gpt-4o.
For large datasets, consider sending summarized or chunked data to avoid token limits.

✅

Key Takeaways

Use the gpt-4o model with the OpenAI Python SDK to run code interpreter tasks for data analysis.
Send your data as text in the user message and ask the model to analyze it using Python code.
Async and streaming calls improve responsiveness for large or complex data analysis.
Always set your API key in os.environ and verify model compatibility for code execution.
Chunk large datasets to stay within token limits and get accurate analysis results.

Verified 2026-04 · gpt-4o, gpt-4o-mini, gpt-4.1

Verify ↗