How to beginner · 3 min read

OpenAI Enterprise custom models

Quick answer

Use the OpenAI Python SDK with your Enterprise API key to call custom models by specifying the model name in client.chat.completions.create. Custom models are accessed like standard models but require your Enterprise account and API key.

PREREQUISITES

Python 3.8+
OpenAI Enterprise API key
pip install openai>=1.0

Setup

Install the official OpenAI Python SDK and set your Enterprise API key as an environment variable.

bash

pip install openai>=1.0

output

Collecting openai
  Downloading openai-1.x.x-py3-none-any.whl
Installing collected packages: openai
Successfully installed openai-1.x.x

Step by step

Use the OpenAI SDK to call your Enterprise custom model by specifying its exact model name. Replace YOUR_ENTERPRISE_MODEL with your custom model ID.

python

import os
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

response = client.chat.completions.create(
    model="YOUR_ENTERPRISE_MODEL",
    messages=[{"role": "user", "content": "Explain RAG in simple terms."}]
)

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

output

Retrieval-Augmented Generation (RAG) is a technique that combines retrieval of relevant documents with generation of answers, improving accuracy and context.

Common variations

You can use async calls, streaming, or switch between different Enterprise custom models by changing the model parameter. Streaming allows partial token output for faster response.

python

import os
import asyncio
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])

async def main():
    stream = await client.chat.completions.create(
        model="YOUR_ENTERPRISE_MODEL",
        messages=[{"role": "user", "content": "Summarize AI trends."}],
        stream=True
    )
    async for chunk in stream:
        print(chunk.choices[0].delta.content or "", end="", flush=True)

asyncio.run(main())

output

AI trends include increased adoption of generative models, improved multimodal capabilities, and wider enterprise integration.

Troubleshooting

If you get 401 Unauthorized, verify your Enterprise API key is set correctly in OPENAI_API_KEY.
If model not found error occurs, confirm your custom model name is correct and accessible in your Enterprise account.
For rate limits, check your Enterprise quota and usage dashboard.

✅

Key Takeaways

Use the OpenAI Python SDK with your Enterprise API key to access custom models by specifying their model names.
Custom models behave like standard OpenAI models but require Enterprise account permissions.
Streaming and async calls improve responsiveness and flexibility with Enterprise custom models.

Verified 2026-04 · YOUR_ENTERPRISE_MODEL

Verify ↗