nvidia/llama-3.3-nemotron-super-49b-v1.5

from openai import OpenAI

client = OpenAI(
  base_url = "https://integrate.api.nvidia.com/v1",
  api_key = "$NVIDIA_API_KEY"
)

completion = client.chat.completions.create(
  model="nvidia/llama-3.3-nemotron-super-49b-v1.5",
  messages=[{"role":"user","content":""}],
  temperature=0.6,
  top_p=0.95,
  max_tokens=65536,
  frequency_penalty=0,
  presence_penalty=0,
  stream=False
)

print(completion.choices[0].message)