nvidia/Llama-3_1-Nemotron-Ultra-253B-v1

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AIHUBMIX_API_KEY"],
    base_url="https://shkq.org/v1",
)

response = client.chat.completions.create(
    model="nvidia/Llama-3_1-Nemotron-Ultra-253B-v1",
    messages=[
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    max_tokens=1024,
    stream=False,
)

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