GPT-4o Vision lets you send images to the API and ask questions about them — receipts, screenshots, diagrams, photos, documents.

Sending an Image

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What's in this image?"},
            {
                "type": "image_url",
                "image_url": {"url": "https://example.com/photo.jpg"}
            }
        ]
    }]
)

Also Works With Base64

For local images, encode as base64 and use "url": "data:image/jpeg;base64,{base64_string}"

Reference:

Vision API documentation

https://en.wikipedia.org/wiki/Special:Search?search=Vision