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="openai/gpt-oss-20b",
messages=[{"role":"user","content":""}],
temperature=1,
top_p=1,
max_tokens=4096,
stream=False
)
reasoning = getattr(completion.choices[0].message, "reasoning_content", None)
if reasoning:
print(reasoning)
print(completion.choices[0].message.content)Deploy this model now on your endpoint provider of choice