make_req.py

import httpx
import time
time.sleep(2)
try:
    res = httpx.post("http://127.0.0.1:8001/v1/messages", json={
        "model": "nvidia/nemotron",
        "messages": [{"role": "user", "content": "hi"}],
        "max_tokens": 10
    }, headers={"Authorization": "Bearer TEST"})
    print(res.status_code)
    print(res.text)
except Exception as e:
    print(f"Error: {e}")