Azure OpenAI in Azure AI Foundry models

Azure OpenAI is powered by a diverse set of models with different capabilities and price points. Model availability varies by region and cloud. For Azure Government model availability, refer to Azure OpenAI in Azure Government.

GPT-5

Region availability

• Registration is required for access to the gpt-5 model.

• gpt-5-mini, gpt-5-nano, and gpt-5-chat do not require registration.

Access will be granted based on Microsoft's eligibility criteria. Customers who previously applied and received access to o3, don't need to reapply as their approved subscriptions will automatically be granted access upon model release.

gpt-oss

Region availability

Capabilities

¹ Unlike other Azure OpenAI models gpt-oss-120b requires an Azure AI Foundry project to deploy the model.

Deploy with code

az cognitiveservices account deployment create \
  --name "Foundry-project-resource" \
  --resource-group "test-rg" \
  --deployment-name "gpt-oss-120b" \
  --model-name "gpt-oss-120b" \
  --model-version "1" \
  --model-format "OpenAI-OSS" \
  --sku-capacity 10 \
  --sku-name "GlobalStandard"

GPT-4.1 series

Region availability

Capabilities

model-router

A model that intelligently selects from a set of underlying chat models to respond to a given prompt.

Region availability

Capabilities

Larger context windows are compatible with some of the underlying models. That means an API call with a larger context succeeds only if the prompt happens to be routed to the right model. Otherwise, the call fails.

computer-use-preview

An experimental model trained for use with the Responses API computer use tool.

It can be used with third-party libraries to allow the model to control mouse and keyboard input, while getting context from screenshots of the current environment.

Registration is required to access computer-use-preview. Access is granted based on Microsoft's eligibility criteria. Customers who have access to other limited access models still need to request access for this model.

To request access, go to computer-use-preview limited access model application. When access is granted, you need to create a deployment for the model.

Region availability

Capabilities

o-series models

The Azure OpenAI o-series models are designed to tackle reasoning and problem-solving tasks with increased focus and capability. These models spend more time processing and understanding the user's request, making them exceptionally strong in areas like science, coding, and math, compared to previous iterations.

To learn more about advanced o-series models, see Getting started with reasoning models.

Region availability

GPT-4o and GPT-4 Turbo

GPT-4o integrates text and images in a single model, which enables it to handle multiple data types simultaneously. This multimodal approach enhances accuracy and responsiveness in human-computer interactions. GPT-4o matches GPT-4 Turbo in English text and coding tasks while offering superior performance in non-English language tasks and vision tasks, setting new benchmarks for AI capabilities.

How do I access the GPT-4o and GPT-4o mini models?

GPT-4o and GPT-4o mini are available for Standard and Global Standard model deployment.

You need to create or use an existing resource in a supported Standard or Global Standard region where the model is available.

When your resource is created, you can deploy the GPT-4o models. If you're performing a programmatic deployment, the model names are:

• gpt-4o version 2024-11-20
• gpt-4o version 2024-08-06
• gpt-4o version 2024-05-13
• gpt-4o-mini version 2024-07-18

GPT-4 Turbo

GPT-4 Turbo is a large multimodal model (accepting text or image inputs and generating text) that can solve difficult problems with greater accuracy than any of OpenAI's previous models. Like GPT-3.5 Turbo, and older GPT-4 models, GPT-4 Turbo is optimized for chat and works well for traditional completions tasks.

GPT-4

GPT-4 is the predecessor to GPT-4 Turbo. Both the GPT-4 and GPT-4 Turbo models have a base model name of gpt-4. You can distinguish between the GPT-4 and Turbo models by examining the model version.

GPT-4 and GPT-4 Turbo models

These models can be used only with the Chat Completions API.

See Model versions to learn about how Azure OpenAI handles model version upgrades. See Working with models to learn how to view and configure the model version settings of your GPT-4 deployments.

GPT-3.5

GPT-3.5 models can understand and generate natural language or code. The most capable and cost effective model in the GPT-3.5 family is GPT-3.5 Turbo, which is optimized for chat and also works well for traditional completions tasks. GPT-3.5 Turbo is available for use with the Chat Completions API. GPT-3.5 Turbo Instruct has similar capabilities to text-davinci-003 when you use the Completions API instead of the Chat Completions API. We recommend using GPT-3.5 Turbo and GPT-3.5 Turbo Instruct over legacy GPT-3.5 and GPT-3 models.

To learn more about how to interact with GPT-3.5 Turbo and the Chat Completions API, check out our in-depth how-to article.

Embeddings

text-embedding-3-large is the latest and most capable embedding model. You can't upgrade between embeddings models. To move from using text-embedding-ada-002 to text-embedding-3-large, you need to generate new embeddings.

• text-embedding-3-large
• text-embedding-3-small
• text-embedding-ada-002

OpenAI reports that testing shows that both the large and small third generation embeddings models offer better average multi-language retrieval performance with the MIRACL benchmark. They still maintain performance for English tasks with the MTEB benchmark.

The third generation embeddings models support reducing the size of the embedding via a new dimensions parameter. Typically, larger embeddings are more expensive from a compute, memory, and storage perspective. When you can adjust the number of dimensions, you gain more control over overall cost and performance. The dimensions parameter isn't supported in all versions of the OpenAI 1.x Python library. To take advantage of this parameter, we recommend that you upgrade to the latest version: pip install openai --upgrade.

OpenAI's MTEB benchmark testing found that even when the third generation model's dimensions are reduced to less than the 1,536 dimensions of text-embeddings-ada-002, performance remains slightly better.

Image generation models

The image generation models generate images from text prompts that the user provides. GPT-image-1 is in limited access preview. DALL-E 3 is generally available for use with the REST APIs. DALL-E 2 and DALL-E 3 with client SDKs are in preview.

Registration is required to access gpt-image-1. Access is granted based on Microsoft's eligibility criteria. Customers who have access to other limited access models still need to request access for this model.

To request access, go to gpt-image-1 limited access model application. When access is granted, you need to create a deployment for the model.

Region availability

Video generation models

Sora is an AI model from OpenAI that can create realistic and imaginative video scenes from text instructions. Sora is in preview.

Region availability

Audio models

Audio models in Azure OpenAI are available via the realtime, completions, and audio APIs.

GPT-4o audio models

The GPT-4o audio models are part of the GPT-4o model family and support either low-latency, speech in, speech out conversational interactions or audio generation.

Details about maximum request tokens and training data are available in the following table:

To compare the availability of GPT-4o audio models across all regions, refer to the models table.

Audio API

The audio models via the /audio API can be used for speech to text, translation, and text to speech.

Speech-to-text models

Speech translation models

Text-to-speech models (preview)

For more information, see Audio models region availability later in this article.

Model summary table and region availability

Models by deployment type

Azure OpenAI provides customers with choices on the hosting structure that fits their business and usage patterns. The service offers two main types of deployment:

• Standard: Has a global deployment option, routing traffic globally to provide higher throughput.
• Provisioned: Also has a global deployment option, allowing customers to purchase and deploy provisioned throughput units across Azure global infrastructure.

All deployments can perform the exact same inference operations, but the billing, scale, and performance are substantially different. To learn more about Azure OpenAI deployment types, see our Deployment types guide.

This table doesn't include fine-tuning regional availability information. Consult the fine-tuning section for this information.

Standard deployment (regional) models by endpoint

Fine-tuning models

Assistants (preview)

For Assistants, you need a combination of a supported model and a supported region. Certain tools and capabilities require the latest models. The following models are available in the Assistants API, SDK, and Azure AI Foundry. The following table is for standard deployment. For information on provisioned throughput unit availability, see Provisioned throughput. The listed models and regions can be used with both Assistants v1 and v2. You can use Global Standard models if they're supported in the following regions.

Model retirement

For the latest information on model retirements, refer to the model retirement guide.

Related content

• Model retirement and deprecation
• Learn more about working with Azure OpenAI models
• Learn more about Azure OpenAI
• Learn more about fine-tuning Azure OpenAI models