Two ways to run inference,
one compatible API

python

import os

from openai import OpenAI

client = OpenAI(
    base_url=os.environ["ONX_BASE_URL"],
    api_key=os.environ["ONX_API_KEY"],
)

resp = client.chat.completions.create(
    model="glm-5.3",
    messages=[{"role": "user", "content": "Refactor this module"}],
)

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

curl

curl $ONX_BASE_URL/chat/completions \
  -H "Authorization: Bearer $ONX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.3",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

# Base URL and API keys both come from the console