调用此模型
request.py
from openai import OpenAI
client = OpenAI(
base_url="https://api.tokener.ai/v1",
api_key="sk-tk-••••••••••••",
)
response = client.chat.completions.create(
model="qwen-mt-flash",
messages=[{"role": "user", "content": "Explain retrieval augmented generation."}],
)