Microsoft is excited to add OpenAI’s newest models o1-preview and o1-mini to Microsoft Azure OpenAI Service, Azure AI Studio, and GitHub Models. The o1 series enables complex coding, math reasoning, brainstorming, and comparative analysis capabilities, setting a new benchmark for AI-powered solutions.
The o1-preview and o1-mini models are now accessible in Azure AI Studio and GitHub Models to a select group of Azure customers to collaboratively explore and identify the unique strengths of each model. The o1 series of advanced reasoning models excel at complex and nuanced problem spaces like these:
-
Complex Code Generation: Capable of algorithm generation and advanced coding tasks to help developers.
-
Advanced Problem Solving: Perfect for comprehensive brainstorming sessions and tackling multifaceted issues.
-
Complex Document Comparison: Ideal for analyzing contracts, case files, or legal documents to discern subtle differences.
-
Instruction Following and Workflow Management: Particularly adept at handling workflows that require shorter context.
GitHub Copilot, the world’s most widely adopted AI developer tool, has been testing the o1 models, showing promising results in code analysis and optimisation.
New Updates in Microsoft's Commitment to Responsible AI and Safety by Default
Safety remains Microsoft’s top priority in delivering new generative AI models. The o1 and o1-mini models in Azure OpenAI Service include 'on-by-default' Content Safety features, provided at no extra cost to you.
OpenAI has invested in additional safety advancements with these models, including new methods that help the model refuse unsafe requests. This makes the o1 series of models among the most robust models we have deployed to date. You can assess the safety of their AI application and model deployments with Azure AI Studio safety evaluations.
Microsoft continues to expand and enhance the Content Safety systems for all models. They are pleased to announce that Prompt Shields and Protected Materials for Text are now generally available in Azure OpenAI Service. These features help customers safeguard the safety and integrity of their generative AI deployments, preventing potential misuse. Additionally, Microsoft have introduced 'Spotlighting,' a set of techniques designed to help models distinguish between valid instructions and potentially untrusted external inputs. They have updated their documentation explaining how to use “Spotlighting” and related techniques so customers can take advantage of Microsoft’s latest research.
Trying the New Models in Azure AI Studio and GitHub
Microsoft offers a preview of the o1-preview and o1-mini models in Azure AI Studio playground and GitHub Models, available to select customers. This exclusive access enables early experimentation with their advanced reasoning capabilities, with API access coming soon. To get started, visit the Azure AI Studio model catalog and apply for access today.
Navigating Model Lineup
GPT-4o models offer industry-leading capabilities in text and image comprehension, while GPT-4o mini provides high-quality summarisation and Q&A, with cost-effective deployment options and rapid response times. The limitations of these models in solving has been observed, even simple mathematical problems, despite providing strong guidance and examples.
To better understand o1-preview and o1-mini’s place in the model lineup, here’s a quick overview of the key models powering Azure OpenAI Service:
- o1-preview: Focused on advanced reasoning and solving complex problems, including math and science tasks. Ideal for applications that require deep contextual understanding and agentic workflows.
- o1-mini: Smaller and faster, and 80% cheaper than o1-preview, performs well at code generation and small context operations.
- GPT-4o: A versatile, multimodal model that excels in both text and image processing, with superior performance in non-English languages and vision tasks. Suitable for applications needing enhanced accuracy and multilingual capabilities. The model also features JSON Structured Outputs for consistent, well-defined data formats, reducing post-processing needs and improving application efficiency. Designed for real-time applications that require fast, reliable text responses at minimal cost.
- GPT-4o Mini: A smaller, cost-effective version of GPT-4o, optimised for environments with limited resources or high cost constraints. Retains text and image processing capabilities, making it ideal for lightweight applications.
- DALL-E: Generates images from text prompts with safety, ideal for creative content and marketing.
- Whisper: Transcribes and translates speech to text, suitable for real-time transcription and multilingual communication.
These models represent a progression of capabilities, from efficient text processing to advanced reasoning and multimodal functionality. Each model has paved the way for the innovations Microsoft continue to introduce with “o1.”