视觉(图片输入)

{
  "model": "gpt-5.5",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "图里是什么动物?"},
      {"type": "image_url", "image_url": {
        "url": "https://example.com/cat.jpg",
        "detail": "high"
      }}
    ]
  }]
}

import base64
with open("photo.jpg", "rb") as f:
    b64 = base64.b64encode(f.read()).decode()

resp = client.chat.completions.create(
    model="gpt-5.5",
    messages=[{"role": "user", "content": [
        {"type": "text", "text": "描述这张图"},
        {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{b64}"}}
    ]}]
)

{
  "model": "claude-opus-4-8",
  "max_tokens": 1024,
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "OCR 这张图"},
      {"type": "image", "source": {
        "type": "url",
        "url": "https://example.com/doc.png"
      }}
    ]
  }]
}

{"type": "image", "source": {
  "type": "base64",
  "media_type": "image/png",
  "data": "<base64>"
}}

{
  "contents": [{
    "role": "user",
    "parts": [
      {"text": "图里在做什么?"},
      {"inline_data": {"mime_type": "image/png", "data": "<base64>"}}
    ]
  }]
}

{"file_data": {"mime_type": "application/pdf", "file_uri": "https://..."}}

{
  "role": "user",
  "content": [
    {"type": "text", "text": "对比两张图的差异"},
    {"type": "image_url", "image_url": {"url": "https://.../a.jpg"}},
    {"type": "image_url", "image_url": {"url": "https://.../b.jpg"}}
  ]
}