Python

Before you begin

Open a fresh terminal, configure a scoped key and list the models available to your account before using the client. The shared setup includes Bash and PowerShell commands.

• Credentials and model check

Install and configure

Install the official openai package in your virtual environment. Set NOTHOLY_API_KEY and NOTHOLY_MODEL privately. The generated example disables automatic retries and sets an explicit output allowance. A successful generation consumes account credits.

Stream and call tools

Use the Chat Completions reference for incremental text and function calls. Accumulate tool arguments until the terminal tool call is complete; validate them before execution. Python streaming helpers require separate client-version verification.

Client configuration

Select a published model to generate configuration. Confirm your account can use it with GET /v1/models before sending a request.

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["NOTHOLY_API_KEY"],
    base_url="https://api.notholy.com/v1",
    max_retries=0,
)
response = client.chat.completions.create(
    model="notholy-pulse",
    messages=[{"role": "user", "content": "Explain least privilege."}],
    max_tokens=2048,
)
print(response.choices[0].message.content)

Configuration reference: a generated snippet is not a full client certification. Check the compatibility notes above. Keep API keys in your private environment.