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

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.

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.

# 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://dori-uw-1.kuma-moon.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.

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.

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 <a href="https://dori-uw-1.kuma-moon.com/azure/ai-services/openai/how-to/chatgpt?tabs=python&pivots=programming-language-chat-completions" target="_blank">in-depth how-to.</a> # 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-turbo¹ (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 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.

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-turbo¹ (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 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 <a href="https://dori-uw-1.kuma-moon.com/azure/ai-services/openai/how-to/chatgpt?tabs=python&pivots=programming-language-chat-completions" target="_blank">in-depth how-to.</a> # 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

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://dori-uw-1.kuma-moon.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.

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

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

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

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://dori-uw-1.kuma-moon.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.

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

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

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

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

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

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

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

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

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: - Overview of Responsible AI practices for Azure OpenAI models - Transparency Note for Azure OpenAI Service # 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.

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

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.

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

gpt-5.1 is designed for logic-heavy and multi-step tasks.

gpt-5.1-chat (preview) is an advanced, natural, multimodal, and context-aware conversations for enterprise applications.

gpt-5.1-codex is designed for steerability, front end development, and interactivity.

gpt-5.1-codex-max is agentic coding model designed to streamline complex development workflows with advanced efficiency

gpt-5.1-codex-mini is designed for steerability, front end development, and interactivity.

GPT-5.2 is engineered for enterprise agent scenarios—delivering structured, auditable outputs, reliable tool use, and governed integrations.

gpt-5.2-chat (preview) is an advanced, natural, multimodal, and context-aware conversations for enterprise applications.

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

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

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

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

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

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

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

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

An efficient AI solution for diverse text and image tasks, including high quality, cheap text to image generation

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.

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.

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

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.

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

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

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

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

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.

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

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.

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

An efficient AI solution to generate videos

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

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

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.

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.

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.

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.