How to beginner · 3 min read

Azure OpenAI enterprise pricing

Quick answer

Azure OpenAI enterprise pricing is usage-based, billed per 1,000 tokens processed with rates varying by model and region. Use the AzureOpenAI SDK with your enterprise subscription to monitor usage and control costs effectively.

PREREQUISITES

Python 3.8+
Azure OpenAI enterprise subscription
pip install openai>=1.0
Azure OpenAI endpoint and API key

Setup

Install the openai Python package and set environment variables for your Azure OpenAI endpoint and API key.

Set AZURE_OPENAI_API_KEY with your Azure OpenAI key.
Set AZURE_OPENAI_ENDPOINT with your Azure OpenAI resource endpoint URL.
Set AZURE_OPENAI_DEPLOYMENT with your deployed model name.

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 AzureOpenAI client to call your deployed model and track usage for cost management.

python

import os
from openai import AzureOpenAI

client = AzureOpenAI(
    api_key=os.environ["AZURE_OPENAI_API_KEY"],
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    api_version="2024-02-01"
)

response = client.chat.completions.create(
    model=os.environ["AZURE_OPENAI_DEPLOYMENT"],
    messages=[{"role": "user", "content": "What is the pricing model for Azure OpenAI enterprise?"}]
)
print(response.choices[0].message.content)

output

Azure OpenAI enterprise pricing is based on the number of tokens processed, with rates varying by model and region. You are billed monthly based on your usage.

Common variations

You can use different deployed models by changing the model parameter. For asynchronous calls, use async client methods. Streaming responses are supported by setting stream=True in the request.

python

import asyncio
from openai import AzureOpenAI

async def async_chat():
    client = AzureOpenAI(
        api_key=os.environ["AZURE_OPENAI_API_KEY"],
        azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
        api_version="2024-02-01"
    )
    stream = await client.chat.completions.acreate(
        model=os.environ["AZURE_OPENAI_DEPLOYMENT"],
        messages=[{"role": "user", "content": "Explain Azure OpenAI pricing."}],
        stream=True
    )
    async for chunk in stream:
        print(chunk.choices[0].delta.content or "", end="", flush=True)

asyncio.run(async_chat())

output

Azure OpenAI enterprise pricing is usage-based, charged per 1,000 tokens processed. Pricing varies by model and region. You can monitor usage in the Azure portal.

Troubleshooting

If you encounter authentication errors, verify your AZURE_OPENAI_API_KEY and AZURE_OPENAI_ENDPOINT environment variables are correct. For deployment not found errors, confirm your deployment name matches AZURE_OPENAI_DEPLOYMENT. Check Azure portal quotas and billing limits if usage is unexpectedly blocked.

✅

Key Takeaways

Azure OpenAI enterprise pricing is usage-based, billed per 1,000 tokens processed.
Use the AzureOpenAI client with your endpoint and deployment for API calls.
Monitor usage and costs via the Azure portal to avoid unexpected charges.

Verified 2026-04 · gpt-4o, gpt-4o-mini, gpt-4o-mini-2024-07-18

Verify ↗