Skip to content
Docs Try Aspire

OpenAI Fields

Class Fields 69 members
Models published by OpenAI.
CodexMini Section titled CodexMini staticreadonly FoundryModel
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
public static readonly FoundryModel CodexMini
ComputerUsePreview Section titled ComputerUsePreview staticreadonly FoundryModel
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.
public static readonly FoundryModel ComputerUsePreview

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

DALL-E 3 generates images from text prompts that are provided by the user.

Key model capabilities

The image generation API creates an image from a text prompt. It does not edit existing images or create variations.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The provider has not supplied this information.

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

The provider has not supplied this information.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

The provider has not supplied this information.

Optimizing model performance

The provider has not supplied this information.

Additional assets

The provider has not supplied this information.

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.

public static readonly FoundryModel DallE3
Davinci002 Section titled Davinci002 staticreadonly FoundryModel

Azure Direct Models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all as part of one Azure AI Foundry platform.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Azure AI Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

The provider has not supplied this information.

Key model capabilities

Davinci-002 supports fine-tuning, allowing developers and businesses to customize the model for specific applications.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The provider has not supplied this information.

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

This model supports 16384 max input tokens and training data is up to Sep 2021.

Training time

The provider has not supplied this information.

Input formats

Your training data and validation data sets consist of input and output examples for how you would like the model to perform. The training and validation data you use must be formatted as a JSON Lines (JSONL) document in which each line represents a single prompt-completion pair.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

Davinci-002 is the latest version of Davinci, a gpt-3 based model.

Long context

This model supports 16384 max input tokens.

Optimizing model performance

The provider has not supplied this information.

Additional assets

Learn more at https://learn.microsoft.com/azure/cognitive-services/openai/concepts/models

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.

public static readonly FoundryModel Davinci002
Gpt35Turbo Section titled Gpt35Turbo staticreadonly FoundryModel

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

The gpt-35-turbo is a language model designed for conversational interfaces that has been optimized for chat using the Chat Completions API.

Key model capabilities

The provider has not supplied this information.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The provider has not supplied this information.

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

The model expects a prompt string formatted in a specific chat-like transcript format.

Output formats

The model returns a completion that represents a model-written message in the chat.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

The provider has not supplied this information.

Optimizing model performance

The provider has not supplied this information.

Additional assets

The provider has not supplied this information.

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.

public static readonly FoundryModel Gpt35Turbo
Gpt35Turbo16k Section titled Gpt35Turbo16k staticreadonly FoundryModel

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

gpt-3.5 models can understand and generate natural language or code.

Key model capabilities

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 using the Completions API instead of the Chat Completions API.

To learn more about how to interact with gpt-3.5-turbo and the Chat Completions API check out our in-depth how-to. in-depth how-to.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The provider has not supplied this information.

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

Sep 2021

Training time

The provider has not supplied this information.

Input formats

The provider has not supplied this information.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

You can see the token context length supported by each model in the model summary table.

Model ID

Model Availability

Max Request (tokens)

Training Data (up to)

gpt-35-turbo 1 1 (0301)

East US, France Central, South Central US, UK South, West Europe

4,096

Sep 2021

gpt-35-turbo (0613)

Australia East, Canada East, East US, East US 2, France Central, Japan East, North Central US, Sweden Central, Switzerland North, UK South

4,096

Sep 2021

gpt-35-turbo-16k (0613)

Australia East, Canada East, East US, East US 2, France Central, Japan East, North Central US, Sweden Central, Switzerland North, UK South

16,384

Sep 2021

gpt-35-turbo-instruct (0914)

East US, Sweden Central

4,097

Sep 2021

gpt-35-turbo (1106)

Australia East, Canada East, France Central, South India, Sweden Central, UK South, West US

Input: 16,385 Output: 4,096

Sep 2021

1 1 This model will accept requests > 4,096 tokens. It is not recommended to exceed the 4,096 input token limit as the newer version of the model are capped at 4,096 tokens. If you encounter issues when exceeding 4,096 input tokens with this model this configuration is not officially supported.

Optimizing model performance

The provider has not supplied this information.

Additional assets

The provider has not supplied this information.

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.

public static readonly FoundryModel Gpt35Turbo16k
Gpt35TurboInstruct Section titled Gpt35TurboInstruct staticreadonly FoundryModel

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

gpt-3.5 models can understand and generate natural language or code.

Key model capabilities

  • Understand and generate natural language

  • Generate code

  • Chat optimized interactions

  • Traditional completions tasks

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The provider has not supplied this information.

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

Sep 2021

Training time

The provider has not supplied this information.

Input formats

The provider has not supplied this information.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

You can see the token context length supported by each model in the model summary table.

Model ID

Model Availability

Max Request (tokens)

Training Data (up to)

gpt-35-turbo 1 1 (0301)

East US, France Central, South Central US, UK South, West Europe

4,096

Sep 2021

gpt-35-turbo (0613)

Australia East, Canada East, East US, East US 2, France Central, Japan East, North Central US, Sweden Central, Switzerland North, UK South

4,096

Sep 2021

gpt-35-turbo-16k (0613)

Australia East, Canada East, East US, East US 2, France Central, Japan East, North Central US, Sweden Central, Switzerland North, UK South

16,384

Sep 2021

gpt-35-turbo-instruct (0914)

East US, Sweden Central

4,097

Sep 2021

gpt-35-turbo (1106)

Australia East, Canada East, France Central, South India, Sweden Central, UK South, West US

Input: 16,385 Output: 4,096

Sep 2021

1 1 This model will accept requests > 4,096 tokens. It is not recommended to exceed the 4,096 input token limit as the newer version of the model are capped at 4,096 tokens. If you encounter issues when exceeding 4,096 input tokens with this model this configuration is not officially supported.

Optimizing model performance

The provider has not supplied this information.

Additional assets

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

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

public static readonly FoundryModel Gpt35TurboInstruct

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

gpt-4 is a large multimodal model that can solve complex problems with greater accuracy than any of our previous models, thanks to its extensive general knowledge and advanced reasoning capabilities.

Key model capabilities

  • gpt-4-turbo-2024-04-09: This is the GPT-4 Turbo with Vision GA model. It can return up to 4,096 output tokens.

  • gpt-4-1106-preview (GPT-4 Turbo): The latest gpt-4 model with improved instruction following, JSON mode, reproducible outputs, parallel function calling, and more. It returns a maximum of 4,096 output tokens.

  • gpt-4-vision Preview (GPT-4 Turbo with vision): This multimodal AI model enables users to direct the model to analyze image inputs they provide, along with all the other capabilities of GPT-4 Turbo. It can return up to 4,096 output tokens.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The provider has not supplied this information.

Out of scope use cases

Please note that AzureML Studio only supports the deployment of the gpt-4-0314 model version and AI Studio supports the deployment of all the model versions listed below. This preview model is not yet suited for production traffic. As a preview model version, it is not yet suitable for production traffic. This model version will be retired no earlier than July 5, 2024.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

gpt-4 provides a wide range of model versions to fit your business needs:

  • gpt-4-turbo-2024-04-09: The training data is current up to December 2023.

  • gpt-4-1106-preview (GPT-4 Turbo): Training Data: Up to April 2023.

  • gpt-4-vision Preview (GPT-4 Turbo with vision): Training data is current up to April 2023.

  • gpt-4-0613: Training data up to September 2021.

  • gpt-4-0314: Training data up to September 2021.

Training time

The provider has not supplied this information.

Input formats

gpt-4 is a large multimodal model that accepts text or image inputs.

Output formats

gpt-4 outputs text.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

gpt-4 provides different context window sizes across model versions:

  • gpt-4-turbo-2024-04-09: The context window is 128,000 tokens.

  • gpt-4-1106-preview (GPT-4 Turbo): Context window: 128,000 tokens.

  • gpt-4-vision Preview (GPT-4 Turbo with vision): The context window is 128,000 tokens.

  • gpt-4-0613: gpt-4 model with a context window of 8,192 tokens.

  • gpt-4-0314: gpt-4 legacy model with a context window of 8,192 tokens.

Optimizing model performance

The provider has not supplied this information.

Additional assets

Learn more at https://learn.microsoft.com/azure/cognitive-services/openai/concepts/models

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.

public static readonly FoundryModel Gpt4
gpt-4.1 outperforms gpt-4o across the board, with major gains in coding, instruction following, and long-context understanding
public static readonly FoundryModel Gpt41
Gpt41Mini Section titled Gpt41Mini staticreadonly FoundryModel
gpt-4.1-mini outperform gpt-4o-mini across the board, with major gains in coding, instruction following, and long-context handling
public static readonly FoundryModel Gpt41Mini
Gpt41Nano Section titled Gpt41Nano staticreadonly FoundryModel
gpt-4.1-nano provides gains in coding, instruction following, and long-context handling along with lower latency and cost
public static readonly FoundryModel Gpt41Nano
Gpt432k Section titled Gpt432k staticreadonly FoundryModel

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

gpt-4 can solve difficult problems with greater accuracy than any of the previous OpenAI models. Like gpt-35-turbo, gpt-4 is optimized for chat but works well for traditional completions tasks.

Key model capabilities

gpt-4 can solve difficult problems with greater accuracy than any of the previous OpenAI models. Like gpt-35-turbo, gpt-4 is optimized for chat but works well for traditional completions tasks.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

gpt-4 is optimized for chat but works well for traditional completions tasks.

Out of scope use cases

this model can be deployed for inference, but cannot be finetuned.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

The gpt-4 supports 8192 max input tokens and the gpt-4-32k supports up to 32,768 tokens.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

The gpt-4 supports 8192 max input tokens and the gpt-4-32k supports up to 32,768 tokens.

Optimizing model performance

The provider has not supplied this information.

Additional assets

Learn more at https://learn.microsoft.com/azure/cognitive-services/openai/concepts/models

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.

public static readonly FoundryModel Gpt432k
Gpt45Preview Section titled Gpt45Preview staticreadonly FoundryModel
the largest and strongest general purpose model in the gpt model family up to date, best suited for diverse text and image tasks.
public static readonly FoundryModel Gpt45Preview
OpenAI's most advanced multimodal model in the gpt-4o family. Can handle both text and image inputs.
public static readonly FoundryModel Gpt4o
Gpt4oAudioPreview Section titled Gpt4oAudioPreview staticreadonly FoundryModel
Best suited for rich, asynchronous audio input/output interactions, such as creating spoken summaries from text.
public static readonly FoundryModel Gpt4oAudioPreview
Gpt4oMini Section titled Gpt4oMini staticreadonly FoundryModel
An affordable, efficient AI solution for diverse text and image tasks.
public static readonly FoundryModel Gpt4oMini
Gpt4oMiniAudioPreview Section titled Gpt4oMiniAudioPreview staticreadonly FoundryModel
Best suited for rich, asynchronous audio input/output interactions, such as creating spoken summaries from text.
public static readonly FoundryModel Gpt4oMiniAudioPreview
Gpt4oMiniRealtimePreview Section titled Gpt4oMiniRealtimePreview staticreadonly FoundryModel
Best suited for rich, asynchronous audio input/output interactions, such as creating spoken summaries from text.
public static readonly FoundryModel Gpt4oMiniRealtimePreview
Gpt4oMiniTranscribe Section titled Gpt4oMiniTranscribe staticreadonly FoundryModel
A highly efficient and cost effective speech-to-text solution that deliverables reliable and accurate transcripts.
public static readonly FoundryModel Gpt4oMiniTranscribe
Gpt4oMiniTts Section titled Gpt4oMiniTts staticreadonly FoundryModel
An advanced text-to-speech solution designed to convert written text into natural-sounding speech.
public static readonly FoundryModel Gpt4oMiniTts
Gpt4oRealtimePreview Section titled Gpt4oRealtimePreview staticreadonly FoundryModel

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

Introducing our new multimodal AI model, which now supports both text and audio modalities.

Key model capabilities

  • Enhanced customer service: By integrating audio inputs, gpt-4o-realtime-preview enables more dynamic and comprehensive customer support interactions.

  • Content innovation: Use gpt-4o-realtime-preview's generative capabilities to create engaging and diverse audio content, catering to a broad range of consumer preferences.

  • Real-time translation: Leverage gpt-4o-realtime-preview's capability to provide accurate and immediate translations, facilitating seamless communication across different languages

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The introduction of gpt-4o-realtime-preview opens numerous possibilities for businesses in various sectors: Enhanced customer service, content innovation, and real-time translation capabilities facilitate seamless communication across different languages.

Out of scope use cases

Currently, the gpt-4o-realtime-preview model focuses on text and audio and does not support existing gpt-4o features such as image modality and structured outputs. For many tasks, the generally available gpt-4o models may still be more suitable.

IMPORTANT: At this time, gpt-4o-realtime-preview usage limits are suitable for test and development. To prevent abuse and preserve service integrity, rate limits will be adjusted as needed.

IMPORTANT: The system stores your prompts and completions as described in the "Data Use and Access for Abuse Monitoring" section of the service-specific Product Terms for Azure OpenAI Service, except that the Limited Exception does not apply. Abuse monitoring will be turned on for use of the GPT-4o-realtime-preview API even for customers who otherwise are approved for modified abuse monitoring.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

Currently, the gpt-4o-realtime-preview model focuses on text and audio and does not support existing gpt-4o features such as image modality and structured outputs.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

The provider has not supplied this information.

Optimizing model performance

The provider has not supplied this information.

Additional assets

The following documents are applicable:

Training disclosure

Training, testing and validation

GPT-4o-realtime-preview has safety built-in by design across modalities, through techniques such as filtering training data and refining the model's behavior through post-training.

Distribution

Distribution channels

The provider has not supplied this information.

More information

We've evaluated GPT-4o-realtime-preview according to our Preparedness Framework and in line with our voluntary commitments. Our evaluations of cybersecurity, CBRN, persuasion, and model autonomy show that GPT-4o-realtime-preview does not score above Medium risk in any of these categories. This assessment involved running a suite of automated and human evaluations throughout the model training process. We tested both pre-safety-mitigation and post-safety-mitigation versions of the model, using custom fine-tuning and prompts, to better elicit model capabilities.

GPT-4o-realtime-preview has also undergone extensive external red teaming with 70+ external experts in domains such as social psychology, bias and fairness, and misinformation to identify risks that are introduced or amplified by the newly added modalities. We used these learnings to build out our safety interventions in order to improve the safety of interacting with GPT-4o-realtime-preview. We will continue to mitigate new risks as they're discovered.

Model Versions:

  • 2024-12-17: Updating the gpt-4o-realtime-preview model with improvements in voice quality and input reliability. As this is a preview version, it is designed for testing and feedback purposes and is not yet optimized for production traffic.

  • 2024-10-01: Introducing our new multimodal AI model, which now supports both text and audio modalities. As this is a preview version, it is designed for testing and feedback purposes and is not yet optimized for production traffic.

public static readonly FoundryModel Gpt4oRealtimePreview
Gpt4oTranscribe Section titled Gpt4oTranscribe staticreadonly FoundryModel
A cutting-edge speech-to-text solution that deliverables reliable and accurate transcripts.
public static readonly FoundryModel Gpt4oTranscribe
Gpt4oTranscribeDiarize Section titled Gpt4oTranscribeDiarize staticreadonly FoundryModel
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.
public static readonly FoundryModel Gpt4oTranscribeDiarize
gpt-5 is designed for logic-heavy and multi-step tasks.
public static readonly FoundryModel Gpt5
gpt-5.1 is designed for logic-heavy and multi-step tasks.
public static readonly FoundryModel Gpt51
Gpt51Chat Section titled Gpt51Chat staticreadonly FoundryModel
gpt-5.1-chat (preview) is an advanced, natural, multimodal, and context-aware conversations for enterprise applications.
public static readonly FoundryModel Gpt51Chat
Gpt51Codex Section titled Gpt51Codex staticreadonly FoundryModel
gpt-5.1-codex is designed for steerability, front end development, and interactivity.
public static readonly FoundryModel Gpt51Codex
Gpt51CodexMax Section titled Gpt51CodexMax staticreadonly FoundryModel
gpt-5.1-codex-max is agentic coding model designed to streamline complex development workflows with advanced efficiency
public static readonly FoundryModel Gpt51CodexMax
Gpt51CodexMini Section titled Gpt51CodexMini staticreadonly FoundryModel
gpt-5.1-codex-mini is designed for steerability, front end development, and interactivity.
public static readonly FoundryModel Gpt51CodexMini
GPT-5.2 is engineered for enterprise agent scenarios—delivering structured, auditable outputs, reliable tool use, and governed integrations.
public static readonly FoundryModel Gpt52
Gpt52Chat Section titled Gpt52Chat staticreadonly FoundryModel
gpt-5.2-chat (preview) is an advanced, natural, multimodal, and context-aware conversations for enterprise applications.
public static readonly FoundryModel Gpt52Chat
Gpt52Codex Section titled Gpt52Codex staticreadonly FoundryModel
gpt-5.2-codex is designed for steerability, front end development, and interactivity.
public static readonly FoundryModel Gpt52Codex
Gpt53Chat Section titled Gpt53Chat staticreadonly FoundryModel
gpt-5.3-chat (preview) is an advanced, natural, multimodal, and context-aware conversations for enterprise applications.
public static readonly FoundryModel Gpt53Chat
Gpt53Codex Section titled Gpt53Codex staticreadonly FoundryModel
gpt-5.3-codex is designed for steerability, front end development, and interactivity.
public static readonly FoundryModel Gpt53Codex
GPT‑5.4 is OpenAI’s most capable frontier model, built to deliver faster, more reliable results for complex professional work.
public static readonly FoundryModel Gpt54
Gpt54Mini Section titled Gpt54Mini staticreadonly FoundryModel
GPT‑5.4‑mini is a compact, cost‑efficient model designed for reliable performance across high‑volume, everyday AI workloads.
public static readonly FoundryModel Gpt54Mini
Gpt54Nano Section titled Gpt54Nano staticreadonly FoundryModel
GPT‑5.4‑nano is a lightweight, ultra‑efficient model designed for low‑latency, cost‑effective tasks at massive scale.
public static readonly FoundryModel Gpt54Nano
Gpt54Pro Section titled Gpt54Pro staticreadonly FoundryModel
GPT‑5.4-Pro is OpenAI’s most capable frontier model, built to deliver faster, more reliable results for complex professional work.
public static readonly FoundryModel Gpt54Pro
Gpt5Chat Section titled Gpt5Chat staticreadonly FoundryModel
gpt-5-chat (preview) is an advanced, natural, multimodal, and context-aware conversations for enterprise applications.
public static readonly FoundryModel Gpt5Chat
Gpt5Codex Section titled Gpt5Codex staticreadonly FoundryModel
gpt-5-codex is designed for steerability, front end development, and interactivity.
public static readonly FoundryModel Gpt5Codex
Gpt5Mini Section titled Gpt5Mini staticreadonly FoundryModel
gpt-5-mini is a lightweight version for cost-sensitive applications.
public static readonly FoundryModel Gpt5Mini
Gpt5Nano Section titled Gpt5Nano staticreadonly FoundryModel
gpt-5-nano is optimized for speed, ideal for applications requiring low latency.
public static readonly FoundryModel Gpt5Nano
Gpt5Pro Section titled Gpt5Pro staticreadonly FoundryModel
gpt-5-pro uses more compute to think harder and provide consistently better answers.
public static readonly FoundryModel Gpt5Pro
GptAudio Section titled GptAudio staticreadonly FoundryModel
Best suited for rich, asynchronous audio input/output interactions, such as creating spoken summaries from text.
public static readonly FoundryModel GptAudio
GptAudio15 Section titled GptAudio15 staticreadonly FoundryModel
A new S2S (speech to speech) model with improved instruction following.
public static readonly FoundryModel GptAudio15
GptAudioMini Section titled GptAudioMini staticreadonly FoundryModel
Best suited for rich, asynchronous audio input/output interactions, such as creating spoken summaries from text.
public static readonly FoundryModel GptAudioMini
GptImage1 Section titled GptImage1 staticreadonly FoundryModel
An efficient AI solution for diverse text and image tasks, including text to image, image to image, inpainting, and prompt transformation.
public static readonly FoundryModel GptImage1
GptImage15 Section titled GptImage15 staticreadonly FoundryModel
An efficient AI solution for diverse text and image tasks, including high quality, and editing scenarios
public static readonly FoundryModel GptImage15
GptImage1Mini Section titled GptImage1Mini staticreadonly FoundryModel
An efficient AI solution for diverse text and image tasks, including high quality, cheap text to image generation
public static readonly FoundryModel GptImage1Mini
GptOss120b Section titled GptOss120b staticreadonly FoundryModel
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.
public static readonly FoundryModel GptOss120b
GptOss20b Section titled GptOss20b staticreadonly FoundryModel
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.
public static readonly FoundryModel GptOss20b
GptRealtime Section titled GptRealtime staticreadonly FoundryModel
A new S2S (speech to speech) model with improved instruction following.
public static readonly FoundryModel GptRealtime
GptRealtime15 Section titled GptRealtime15 staticreadonly FoundryModel
A new S2S (speech to speech) model with improved instruction following.
public static readonly FoundryModel GptRealtime15
GptRealtimeMini Section titled GptRealtimeMini staticreadonly FoundryModel
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.
public static readonly FoundryModel GptRealtimeMini
Focused on advanced reasoning and solving complex problems, including math and science tasks. Ideal for applications that require deep contextual understanding and agentic workflows.
public static readonly FoundryModel O1
Smaller, faster, and 80% cheaper than o1-preview, performs well at code generation and small context operations.
public static readonly FoundryModel O1Mini
O1Preview Section titled O1Preview staticreadonly FoundryModel
Focused on advanced reasoning and solving complex problems, including math and science tasks. Ideal for applications that require deep contextual understanding and agentic workflows.
public static readonly FoundryModel O1Preview
o3 includes significant improvements on quality and safety while supporting the existing features of o1 and delivering comparable or better performance.
public static readonly FoundryModel O3
O3DeepResearch Section titled O3DeepResearch staticreadonly FoundryModel
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.
public static readonly FoundryModel O3DeepResearch
o3-mini includes the o1 features with significant cost-efficiencies for scenarios requiring high performance.
public static readonly FoundryModel O3Mini
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.
public static readonly FoundryModel O3Pro
o4-mini includes significant improvements on quality and safety while supporting the existing features of o3-mini and delivering comparable or better performance.
public static readonly FoundryModel O4Mini
An efficient AI solution to generate videos
public static readonly FoundryModel Sora
TextEmbedding3Large Section titled TextEmbedding3Large staticreadonly FoundryModel
Text-embedding-3 series models are the latest and most capable embedding model from OpenAI.
public static readonly FoundryModel TextEmbedding3Large
TextEmbedding3Small Section titled TextEmbedding3Small staticreadonly FoundryModel
Text-embedding-3 series models are the latest and most capable embedding model from OpenAI.
public static readonly FoundryModel TextEmbedding3Small
TextEmbeddingAda002 Section titled TextEmbeddingAda002 staticreadonly FoundryModel

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

text-embedding-ada-002 outperforms all the earlier embedding models on text search, code search, and sentence similarity tasks and gets comparable performance on text classification.

Key model capabilities

  • Text search

  • Code search

  • Sentence similarity tasks

  • Text classification

Note: this model can be deployed for inference, specifically for embeddings, but cannot be finetuned.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The provider has not supplied this information.

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

The provider has not supplied this information.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

The provider has not supplied this information.

Optimizing model performance

The provider has not supplied this information.

Additional assets

The provider has not supplied this information.

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.

public static readonly FoundryModel TextEmbeddingAda002

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

TTS is a model that converts text to natural sounding speech. TTS is optimized for realtime or interactive scenarios. For offline scenarios, TTS-HD provides higher quality. The API supports six different voices.

Key model capabilities

  • TTS: optimized for speed.

  • TTS-HD: optimized for quality.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The provider has not supplied this information.

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

Max request data size: 4,096 chars can be converted from text to speech per API request.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

The provider has not supplied this information.

Optimizing model performance

The provider has not supplied this information.

Additional assets

The provider has not supplied this information.

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.

public static readonly FoundryModel Tts

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

TTS-HD is a model that converts text to natural sounding speech.

Key model capabilities

  • TTS: optimized for speed.

  • TTS-HD: optimized for quality.

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

TTS is optimized for realtime or interactive scenarios. For offline scenarios, TTS-HD provides higher quality.

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

Max request data size: 4,096 chars can be converted from text to speech per API request.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

The provider has not supplied this information.

Optimizing model performance

The provider has not supplied this information.

Additional assets

The provider has not supplied this information.

Training disclosure

Training, testing and validation

The provider has not supplied this information.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.

public static readonly FoundryModel TtsHd
Whisper Section titled Whisper staticreadonly FoundryModel

Direct from Azure models

Direct from Azure models are a select portfolio curated for their market-differentiated capabilities:

  • Secure and managed by Microsoft: Purchase and manage models directly through Azure with a single license, consistent support, and no third-party dependencies, backed by Azure's enterprise-grade infrastructure.

  • Streamlined operations: Benefit from unified billing, governance, and seamless PTU portability across models hosted on Azure - all part of Microsoft Foundry.

  • Future-ready flexibility: Access the latest models as they become available, and easily test, deploy, or switch between them within Microsoft Foundry; reducing integration effort.

  • Cost control and optimization: Scale on demand with pay-as-you-go flexibility or reserve PTUs for predictable performance and savings.

Learn more about Direct from Azure models.

Key capabilities

About this model

The Whisper models are trained for speech recognition and translation tasks, capable of transcribing speech audio into the text in the language it is spoken (automatic speech recognition) as well as translated into English (speech translation).

Key model capabilities

  • Speech recognition (automatic speech recognition)

  • Speech translation into English

  • Processing of audio up to 25mb per API request

Use cases

See Responsible AI for additional considerations for responsible use.

Key use cases

The provider has not supplied this information.

Out of scope use cases

The provider has not supplied this information.

Pricing

Pricing is based on a number of factors, including deployment type and tokens used. See pricing details here.

Technical specs

The provider has not supplied this information.

Training cut-off date

The provider has not supplied this information.

Training time

The provider has not supplied this information.

Input formats

Max request data size: 25mb of audio can be converted from speech to text per API request.

Output formats

The provider has not supplied this information.

Supported languages

The provider has not supplied this information.

Sample JSON response

The provider has not supplied this information.

Model architecture

The provider has not supplied this information.

Long context

The provider has not supplied this information.

Optimizing model performance

The provider has not supplied this information.

Additional assets

The provider has not supplied this information.

Training disclosure

Training, testing and validation

Researchers at OpenAI developed the models to study the robustness of speech processing systems trained under large-scale weak supervision.

Distribution

Distribution channels

The provider has not supplied this information.

More information

The provider has not supplied this information.

public static readonly FoundryModel Whisper