Qwen Image

from openai import OpenAI

client = OpenAI(
    api_key="sk-mai-this_a_test_string_please_use_your_generated_key_during_testing",
    base_url="https://mavi-backend.memories.ai/serve/api/v2/iu"
)

resp = client.chat.completions.create(
    model="qwen:qwen3-vl-plus",
    messages=[
        {"role": "system", "content": "You are a multimodal assistant. Keep your answers concise."},
        {
            "role": "user",
            "content": [
                {
                    "image": "https://storage.googleapis.com/memories-test-data/gun5.png"  # url or base64
                },
                {"text": "What is the content of this image?"}
            ]
        }
    ],
    temperature=0.7,  # Controls randomness: 0.0-2.0, higher = more random
    max_tokens=1024,  # Maximum number of tokens to generate
    top_p=0.9,  # Nucleus sampling: 0.0-1.0, consider tokens with top_p probability mass
    frequency_penalty=0.0,  # -2.0 to 2.0, reduces repetition of frequent tokens
    presence_penalty=0.0,  # -2.0 to 2.0, increases likelihood of new topics
    n=1,  # Number of completions to generate
    stream=False,  # Whether to stream the response
    stop=None,  # Stop sequences (list of strings)
    extra_body={
        "metadata": {
            "enable_thinking": True,
            "thinking_budget": 1024,
            "response_format": {
                "type": "json_schema",
                "json_schema": {
                    "name": "answer",
                    "schema": {
                        "type": "object",
                        "properties": {
                            "result": {"type": "string"}
                        },
                        "required": ["result"]
                    }
                }
            }
        }
    }
)
print(resp)