response = client.chat.completions.create(
    model="default",
    messages=[
        {"role": "user", "content": "北京天安门在哪里?"},
    ],
    temperature=0.1,
    metadata={"min_p":0.1},
    stream=False,
)

print(response.choices[0].message.content)
print("\n")

from fastdeploy.engine.sampling_params import SamplingParams
from fastdeploy.entrypoints.llm import LLM

model_name_or_path = "Qwen/Qwen3-0.6B"

sampling_params = SamplingParams(temperature=1.0,min_p=0.1)
llm = LLM(model=model_name_or_path, tensor_parallel_size=1,reasoning_parser="qwen3")
prompt = "北京天安门在哪里?"
messages = [{"role": "user", "content": prompt}]
output = llm.chat([messages],
                   sampling_params)

print(output)