Vision

from openai import OpenAI

client = OpenAI(
  api_key="<AIHUBMIX_API_KEY>",
  base_url="https://aihubmix.com/v1"
)

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://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg",
            "detail": "auto"
          },
        },
      ],
    }
  ],
  max_tokens=300,
)

print(response.choices[0])

{
  "type": "image_url",
  "image_url": {
    "url": "https://example.com/demo.jpg"
  }
}

{
  "type": "image_url",
  "image_url": {
    "url": "data:image/png;base64,<BASE64_DATA>"
  }
}

{
  "role": "user",
  "content": [
    { "type": "text", "text": "Please describe the main content of this image" },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://example.com/photo.jpg"
      }
    }
  ]
}

{
  "role": "user",
  "content": [
    { "type": "text", "text": "Compare the differences between these two images" },
    { "type": "image_url", "image_url": { "url": "https://example.com/a.jpg" } },
    { "type": "image_url", "image_url": { "url": "https://example.com/b.jpg" } }
  ]
}

{
  "image_url": {
    "url": "https://example.com/photo.jpg",
    "detail": "high"
  }
}