NVIDIA: Nemotron 3.5 Lightning

from openai import OpenAI

client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
resp = client.chat.completions.create(
    model="nvidia/nemotron-3.5-lightning",
    messages=[{"role": "user", "content": "Привет"}],
    temperature=0.7,
    max_tokens=1024,
    stream=False,
)
print(resp.choices[0].message.content)

# Стриминг: stream=True — ответ приходит чанками
for chunk in client.chat.completions.create(
    model="nvidia/nemotron-3.5-lightning",
    messages=[{"role": "user", "content": "Привет"}],
    stream=True,
):
    print(chunk.choices[0].delta.content or "", end="", flush=True)