Vision & Multimodal Processing

Pass public image URLs or Base64-encoded strings directly into chat completion messages:

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["MODELMART_API_KEY"],
    base_url="https://api.modelmart.io.vn/v1"
)

response = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this architecture diagram in detail:"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://images.unsplash.com/photo-1551288049-bebda4e38f71"
                    }
                }
            ]
        }
    ]
)

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