多模態輸入

from openai import OpenAI

client = OpenAI(
    api_key="sk-xxx",
    base_url="https://api.onemux.net/v1"
)

response = client.chat.completions.create(
    model="gpt-6.1-sol",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "這張圖片是什麼？"},
                {
                    "type": "image_url",
                    "image_url": {"url": "https://example.com/image.jpg"}
                }
            ]
        }
    ]
)

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

response = client.chat.completions.create(
    model="claude-opus-5-5",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "總結這份 PDF 文件的關鍵資訊"},
                {
                    "type": "image_url",
                    "image_url": {"url": "https://example.com/document.pdf"}
                }
            ]
        }
    ]
)