Last refreshed 2026-09-29. Next refresh: weekly.
Why use babbage on Azure OpenAI?
Azure OpenAI offers babbage with pay-as-you-go pricing at $0.40/1M input tokens. Azure OpenAI Service hosts OpenAI's GPT-4o, GPT-4, GPT-3.5, and embedding models on Microsoft Azure with enterprise SLAs.
Setup recipe
Python + curlpip install openaiexport AZURE_OPENAI_API_KEY=...import os
from openai import AzureOpenAI
client = AzureOpenAI(
azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"], # e.g. https://{resource}.openai.azure.combabbageRequest example
import os
from openai import AzureOpenAI
client = AzureOpenAI(
azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"], # e.g. https://{resource}.openai.azure.com
api_key=os.environ["AZURE_OPENAI_API_KEY"],
api_version="2024-02-01"
)
response = client.chat.completions.create(
model="babbage", # your deployment name
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- babbage is your Azure deployment name, not the underlying model name. Deployment names are set when you deploy a model in Azure AI Foundry / Azure OpenAI Studio.
- The examples expect AZURE_OPENAI_API_KEY; rename it only if your application config maps the new variable.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.40 |
| Output tokens | $0.40 |
Capabilities
No model capability flags are currently sourced.
About babbage
The Babbage model is a large language AI model within the GPT-3 family, recognized for its speed and cost-effectiveness 569. Although it is not as capable as the Davinci model, it outperforms the Ada model in various capabilities 129. Ideal for simpler classification tasks and semantic searches, Babbage efficiently ranks document relevance to search queries 129. With an estimated 1.3 billion parameters 9, it requires less computational power compared to other models like Davinci, which has 175 billion parameters 9.