Production inference through one familiar API.

from openai import OpenAI

client = OpenAI(
    base_url="https://model.inferx.net/v1",
    api_key=INFERX_API_KEY,
)

stream = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello"}],
    stream=True,
)