Azure OpenAI
Azure OpenAIMicrosoft-hosted OpenAI models, including GPT-4 and Codex, offering enterprise-grade security and compliance.

Overview

OpenAI, Inc aims to create "safe and beneficial" artificial general intelligence, defined as highly autonomous systems that outperform humans at most economically valuable work. The organization leads today's AI boom with some of the world's most advanced multimodal foundation models—including GPT‑4o, its real‑time "omni" flagship—and continues to compress state‑of‑the‑art performance into smaller, cheaper variants like GPT‑4o‑mini. The latest GPT‑4o‑transcribe models replace Whisper for speech tasks, while GPT‑Image‑1 overtakes DALL·E 3 with native image generation and editing.

Key Azure AI Foundry Models (July 2025)

  • GPT‑4o – Best‑in‑class reasoning, code, audio & vision in one API.
  • GPT‑4o‑mini – Small‑footprint 20B model that outperforms GPT‑3.5‑Turbo at half the cost.
  • GPT‑4o‑transcribe / TTS – Upgraded speech models with lower error rates and customizable voices.
  • GPT‑Image‑1 – Next‑gen text‑to‑image + in‑painting that supersedes DALL·E 3.

Why OpenAI on Azure

All OpenAI endpoints inherit enterprise‑grade Content Safety, flexible serverless or provisioned‑throughput deployments, Azure billing, and private‑network inference—so you can move from prototype to production in days, not months.
Total Models: 55
gpt-oss-safeguard-120b
gpt-oss-safeguard-120b

Push the open safety model frontier with gpt-oss-safeguard models, released under the permissive Apache 2.0 license, allowing anyone to use, modify, and deploy them freely.

chat-completion
gpt-5-chat
gpt-5-chat

gpt-5-chat (preview) is an advanced, natural, multimodal, and context-aware conversations for enterprise applications.

chat-completion
sora-2
sora-2

Sora 2 in Azure AI Foundry isn’t just another video generation tool; it’s a creative powerhouse, seamlessly integrated into a platform built for innovation, trust, and scale.

video-generation
gpt-4o-transcribe-diarize
gpt-4o-transcribe-diarize

A cutting-edge speech-to-text solution that deliverables reliable and accurate transcripts; now equipped with diarization support aka identifying different speakers through the transcription.

speech-to-text
gpt-5-pro
gpt-5-pro

gpt-5-pro uses more compute to think harder and provide consistently better answers.

chat-completion
gpt-4.1
gpt-4.1

gpt-4.1 outperforms gpt-4o across the board, with major gains in coding, instruction following, and long-context understanding

chat-completion
gpt-4.1-mini
gpt-4.1-mini

gpt-4.1-mini outperform gpt-4o-mini across the board, with major gains in coding, instruction following, and long-context handling

chat-completion
gpt-5-codex
gpt-5-codex

gpt-5-codex is designed for steerability, front end development, and interactivity.

responses
o3
o3

o3 includes significant improvements on quality and safety while supporting the existing features of o1 and delivering comparable or better performance.

chat-completion
gpt-realtime-mini
gpt-realtime-mini

gpt-realtime-mini is a smaller version of gpt-realtime S2S (speech to speech) model built on chive architecture. This model excels at instruction following and is optimized for cost efficiency.

audio-generation
gpt-5
gpt-5

gpt-5 is designed for logic-heavy and multi-step tasks.

chat-completion
gpt-5-mini
gpt-5-mini

gpt-5-mini is a lightweight version for cost-sensitive applications.

chat-completion
gpt-5-nano
gpt-5-nano

gpt-5-nano is optimized for speed, ideal for applications requiring low latency.

chat-completion
o4-mini
o4-mini

o4-mini includes significant improvements on quality and safety while supporting the existing features of o3-mini and delivering comparable or better performance.

chat-completion
gpt-4.1-nano
gpt-4.1-nano

gpt-4.1-nano provides gains in coding, instruction following, and long-context handling along with lower latency and cost

chat-completion
o3-mini
o3-mini

o3-mini includes the o1 features with significant cost-efficiencies for scenarios requiring high performance.

chat-completion
gpt-audio-mini
gpt-audio-mini

Best suited for rich, asynchronous audio input/output interactions, such as creating spoken summaries from text.

audio-generation
gpt-realtime
gpt-realtime

A new S2S (speech to speech) model with improved instruction following.

audio-generation
gpt-audio
gpt-audio

Best suited for rich, asynchronous audio input/output interactions, such as creating spoken summaries from text.

audio-generation
gpt-4.5-preview
gpt-4.5-preview

the largest and strongest general purpose model in the gpt model family up to date, best suited for diverse text and image tasks.

chat-completion
o3-pro
o3-pro

The o3 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.

responses
codex-mini
codex-mini

codex-mini is a fine-tuned variant of the o4-mini model, designed to deliver rapid, instruction-following performance for developers working in CLI workflows. Whether you're automating shell commands, editing scripts, or refactoring repositories, Codex-Min

responses
sora
sora

An efficient AI solution to generate videos

video-generation
gpt-image-1
gpt-image-1

An efficient AI solution for diverse text and image tasks, including text to image, image to image, inpainting, and prompt transformation.

text-to-image
image-to-image
gpt-4o-mini-tts
gpt-4o-mini-tts

An advanced text-to-speech solution designed to convert written text into natural-sounding speech.

text-to-speech
gpt-4o-transcribe
gpt-4o-transcribe

A cutting-edge speech-to-text solution that deliverables reliable and accurate transcripts.

speech-to-text
gpt-4o-mini-transcribe
gpt-4o-mini-transcribe

A highly efficient and cost effective speech-to-text solution that deliverables reliable and accurate transcripts.

speech-to-text
computer-use-preview
computer-use-preview

computer-use-preview is the model for Computer Use Agent for use in Responses API. You can use computer-use-preview model to get instructions to control a browser on your computer screen and take action on a user's behalf.

responses
gpt-4o-mini-audio-preview
gpt-4o-mini-audio-preview

Best suited for rich, asynchronous audio input/output interactions, such as creating spoken summaries from text.

audio-generation
gpt-4o-mini-realtime-preview
gpt-4o-mini-realtime-preview

Best suited for rich, asynchronous audio input/output interactions, such as creating spoken summaries from text.

audio-generation
o1
o1

Focused on advanced reasoning and solving complex problems, including math and science tasks. Ideal for applications that require deep contextual understanding and agentic workflows.

chat-completion
o1-mini
o1-mini

Smaller, faster, and 80% cheaper than o1-preview, performs well at code generation and small context operations.

chat-completion
gpt-4o
gpt-4o

OpenAI's most advanced multimodal model in the gpt-4o family. Can handle both text and image inputs.

chat-completion
gpt-4o-mini
gpt-4o-mini

An affordable, efficient AI solution for diverse text and image tasks.

chat-completion
gpt-4o-audio-preview
gpt-4o-audio-preview

Best suited for rich, asynchronous audio input/output interactions, such as creating spoken summaries from text.

audio-generation
gpt-4o-realtime-preview
gpt-4o-realtime-preview

Azure Direct Models Direct from Azure models are a select portfolio curated for their marketdifferentiated capabilities: Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no thirdparty dependencies, backed by Az

audio-generation
o1-preview
o1-preview

Focused on advanced reasoning and solving complex problems, including math and science tasks. Ideal for applications that require deep contextual understanding and agentic workflows.

chat-completion
gpt-4
gpt-4

Azure Direct Models Direct from Azure models are a select portfolio curated for their marketdifferentiated capabilities: Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no thirdparty dependencies, backed by Az

chat-completion
dall-e-3
dall-e-3

Azure Direct Models Direct from Azure models are a select portfolio curated for their marketdifferentiated capabilities: Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no thirdparty dependencies, backed by Az

text-to-image
davinci-002
davinci-002

Azure Direct Models Direct from Azure models are a select portfolio curated for their marketdifferentiated capabilities: Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no thirdparty dependencies, backed by Az

completions
gpt-35-turbo-16k
gpt-35-turbo-16k

Azure Direct Models Direct from Azure models are a select portfolio curated for their marketdifferentiated capabilities: Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no thirdparty dependencies, backed by Az

chat-completion
gpt-35-turbo-instruct
gpt-35-turbo-instruct

Azure Direct Models Direct from Azure models are a select portfolio curated for their marketdifferentiated capabilities: Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no thirdparty dependencies, backed by Az

chat-completion
gpt-35-turbo
gpt-35-turbo

Azure Direct Models Direct from Azure models are a select portfolio curated for their marketdifferentiated capabilities: Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no thirdparty dependencies, backed by Az

chat-completion
gpt-oss-120b
gpt-oss-120b

Push the open model frontier with GPT-OSS models, released under the permissive Apache 2.0 license, allowing anyone to use, modify, and deploy them freely.

chat-completion
tts
tts

Azure Direct Models Direct from Azure models are a select portfolio curated for their marketdifferentiated capabilities: Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no thirdparty dependencies, backed by Az

text-to-speech
gpt-oss-safeguard-20b
gpt-oss-safeguard-20b

Push the open safety model frontier with gpt-oss-safeguard models, released under the permissive Apache 2.0 license, allowing anyone to use, modify, and deploy them freely.

chat-completion
text-embedding-ada-002
text-embedding-ada-002

Azure Direct Models Direct from Azure models are a select portfolio curated for their marketdifferentiated capabilities: Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no thirdparty dependencies, backed by Az

embeddings
text-embedding-3-large
text-embedding-3-large

Text-embedding-3 series models are the latest and most capable embedding model from OpenAI.

embeddings
o3-deep-research
o3-deep-research

The o3 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and provide consistently better answers.

data-generation
gpt-4-32k
gpt-4-32k

Azure Direct Models Direct from Azure models are a select portfolio curated for their marketdifferentiated capabilities: Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no thirdparty dependencies, backed by Az

chat-completion
gpt-oss-20b
gpt-oss-20b

Push the open model frontier with GPT-OSS models, released under the permissive Apache 2.0 license, allowing anyone to use, modify, and deploy them freely.

chat-completion
1