Qwen3.5 Notes

How to Turn Off Thinking

from openai import OpenAI
import os
# Configured by environment variables
client = OpenAI(base_url="https://api.parasail.io/v1",
    api_key=os.environ["PARASAIL_API_KEY"])

messages = [
    {
        "role": "user",
        "content": [
            {
                "type": "text",
                "text": "What is the capital of New York?"
            }
        ]
    }
]

chat_response = client.chat.completions.create(
    model="Qwen/Qwen3.5-35B-A3B",
    messages=messages,
    max_tokens=32768,
    temperature=0.7,
    top_p=0.8,
    presence_penalty=1.5,
    extra_body={
        "top_k": 20,
        "chat_template_kwargs": {"enable_thinking": False},
    }, 
)
print("Chat response:", chat_response)

Last updated