Using GPT-4o (05-13) 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 gpt-4o-2024-05-13 — see the documentation for request format.
3. 3
   You'll be billed $5.00/1M input, $15.00/1M 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="gpt-4o-2024-05-13",  # 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

About GPT-4o (05-13)

GPT-4o, or GPT-4 Omni, is OpenAI's premier multimodal AI model, introduced on May 13, 2024. It is designed to handle and generate content from various input types, including text, audio, and visual data, using a unified model, unlike its predecessors which required separate models for different modalities. This model is notable for its rapid response times averaging 320 milliseconds, which align with human conversational speed, along with being 50% more cost-effective than GPT-4 Turbo. Although it mirrors GPT-4 Turbo in standard benchmark performance, GPT-4o excels in multilingual, audio, and vision tasks. Despite its advancements, it shares the limitation of a knowledge cutoff at October 2023 and is prone to generating incorrect information, like other language models. A more compact and economical version, GPT-4o mini, is also available.