Using babbage on Azure OpenAI

Quick Start

1. 1
   Create an account at Azure OpenAI and generate an API key.
2. 2
   Use the Azure OpenAI SDK or REST API to call babbage — see the documentation for request format.
3. 3
   You'll be billed $0.40/1M input, $0.40/1M output tokens. See full pricing.

Code Examples

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)

About Azure OpenAI

Azure OpenAI Service hosts OpenAI's GPT-4o, GPT-4, GPT-3.5, and embedding models on Microsoft Azure with enterprise SLAs. Deployments run in customer-selected regions with private networking, role-based access control, and capacity options spanning Standard pay-per-token, Provisioned Throughput Units (PTUs) for reserved capacity, Global Standard shared capacity, and Batch processing. Azure OpenAI sits inside the wider Microsoft Foundry / Azure AI Studio control plane, which adds an evaluation, monitoring, and Agent Service layer on top of the base model APIs. For workloads that need non-OpenAI models (Claude, DeepSeek, Grok, Llama, Mistral, NVIDIA Nemotron), Microsoft Foundry is the broader catalog; Azure OpenAI is the OpenAI-specific entry point. The service is API-compatible with the OpenAI SDK in most flows, so teams typically swap base URLs and authentication rather than rewriting calls.

Azure OpenAI Service hosts OpenAI's GPT-4o, GPT-4, GPT-3.5, and embedding models on Microsoft Azure with enterprise SLAs. Microsoft's broader AI platform spans Azure Machine Learning, Azure Cognitive Services, and Azure AI Search, plus productivity tools like Microsoft 365 Copilot and developer tooling in Visual Studio and the .NET framework. The platform emphasizes responsible AI, security, and regional compliance.

Pricing on Azure OpenAI

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. Nonetheless, its role has been surpassed by more advanced models, such as GPT-3.5-turbo and GPT-4, known for their superior capabilities and efficiency 2.