Python Vision

from openai import OpenAI

client = OpenAI(api_key="sk-xxx", base_url="https://crazyrouter.com/v1")

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

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

import base64
from openai import OpenAI

client = OpenAI(api_key="sk-xxx", base_url="https://crazyrouter.com/v1")

# Read local image and convert to base64
with open("photo.jpg", "rb") as f:
    image_data = base64.b64encode(f.read()).decode("utf-8")

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": f"data:image/jpeg;base64,{image_data}"
                }
            }
        ]
    }]
)

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

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Compare the differences between these two images"},
            {"type": "image_url", "image_url": {"url": "https://example.com/img1.jpg"}},
            {"type": "image_url", "image_url": {"url": "https://example.com/img2.jpg"}}
        ]
    }]
)

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

response = client.chat.completions.create(
    model="claude-sonnet-4-20250514",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "Describe this image in detail"},
            {
                "type": "image_url",
                "image_url": {
                    "url": f"data:image/png;base64,{image_data}"
                }
            }
        ]
    }],
    max_tokens=1024
)

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