How to beginner · 3 min read

How to send images to GPT-4o API

Q: How to send images to GPT-4o API

To send images to the gpt-4o API, use the chat.completions.create method with messages containing image_url or image_base64 fields inside the message content. The gpt-4o model supports multimodal inputs by accepting images alongside text in the chat messages.

Quick answer

To send images to the gpt-4o API, use the chat.completions.create method with messages containing image_url or image_base64 fields inside the message content. The gpt-4o model supports multimodal inputs by accepting images alongside text in the chat messages.

PREREQUISITES

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

Setup

Install the official OpenAI Python SDK v1+ and set your API key as an environment variable.

bash

pip install openai>=1.0

Step by step

Use the OpenAI client to send a chat completion request to gpt-4o with an image included in the message content as a URL or base64 string. The model will process the image along with any text prompt.

python

import os
from openai import OpenAI

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

messages = [
    {
        "role": "user",
        "content": {
            "text": "Describe this image",
            "image_url": "https://example.com/path/to/image.jpg"
        }
    }
]

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

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

output

A detailed description of the image content printed to the console.

Common variations

Use image_base64 instead of image_url to send images encoded in base64.
Send multiple images by including multiple messages or multiple image fields in one message.
Use async calls with asyncio and await for non-blocking requests.

python

import os
import asyncio
from openai import OpenAI

async def main():
    client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
    messages = [
        {
            "role": "user",
            "content": {
                "text": "Analyze this image",
                "image_base64": "<base64-encoded-image-string>"
            }
        }
    ]
    response = await client.chat.completions.create(
        model="gpt-4o",
        messages=messages
    )
    print(response.choices[0].message.content)

asyncio.run(main())

output

Analysis or description of the base64 image printed asynchronously.

Troubleshooting

If you get an error about unsupported content, verify your message content structure matches the multimodal format with text and image_url or image_base64.
Ensure your API key has access to gpt-4o and multimodal features.
Check image URLs are publicly accessible or base64 strings are correctly encoded.

✅

Key Takeaways

Use the gpt-4o model with chat.completions.create to send images as part of chat messages.
Include images via image_url or image_base64 fields inside the message content dictionary.
Ensure your API key supports multimodal inputs and your image data is accessible and correctly formatted.

Verified 2026-04 · gpt-4o

Verify ↗