OpenAI API

Use the familiar Chat Completions format.

POST · Chat Completionshttps://189.24.66.33/v1/chat/completions

Python SDK

Install openai, then point the client at this site.

from openai import OpenAI

client = OpenAI(
    base_url="https://189.24.66.33/v1",
    api_key="sk-relay-...",
)

response = client.chat.completions.create(
    model="glm-5.3-flash-xploded",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Send HTTP requests directly

curl https://189.24.66.33/v1/chat/completions \
  -H 'Authorization: Bearer sk-relay-...' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "glm-5.3-flash-xploded",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Request parameters

Build conversations with model and messages. Whether temperature, output length and tool-calling options work depends on the chosen model and the upstream API.

The current OpenAI-compatible entry point is Chat Completions; clients should choose this format.