Skip to main content

Using Local Base64-Encoded Images

In this lesson, you'll learn how to send a local image to the GPT-4.1 API by encoding it to Base64 and passing it as a data URI.

Prerequisites​

Install the OpenAI SDK:

pip install openai

Make sure you have a local image (e.g., path_to_your_image.jpg).

The Code​

import base64
from openai import OpenAI

client = OpenAI()

# Function to encode the image
def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode("utf-8")

# Path to your image
image_path = "path_to_your_image.jpg"

# Getting the Base64 string
base64_image = encode_image(image_path)

response = client.responses.create(
    model="gpt-4.1",
    input=[
        {
            "role": "user",
            "content": [
                { "type": "input_text", "text": "what's in this image?" },
                {
                    "type": "input_image",
                    "image_url": f"data:image/jpeg;base64,{base64_image}",
                },
            ],
        }
    ],
)

print(response.output_text)

Explanation​

  • base64.b64encode(...): Converts the binary image into a text format.
  • data:image/jpeg;base64,...: Embeds the image directly without uploading it online.
  • input_image can now reference any local image securely.

Use Case​

Best for:

  • Secure local image analysis
  • Offline workflows with temporary media
  • Avoiding public hosting or uploads