Business Software for Microsoft Foundry

Introducing your daily AI assistant designed to enhance both your professional and personal life. With Copilot, you can optimize your workflow, increase your efficiency, unleash your creativity, and maintain connections with those who matter most—all while seamlessly adapting to your individual preferences. This intelligent companion provides innovative solutions for boosting productivity and creativity, ensuring you stay linked to the people and things that are significant to you. Easily discover what you need, receive pertinent responses to your inquiries, and enjoy online shopping with confidence, knowing you're securing the best deals available. Whether you need answers, inspiration for your creative endeavors, or assistance with your tasks, Copilot is here to transform your ideas into reality effortlessly. Crafting stunning visuals and refining your written work becomes an enjoyable experience, and no matter your interests—be it web browsing, seeking knowledge, tapping into your creative side, or generating valuable content—Copilot opens the door to endless opportunities for exploration and growth. Its versatility makes it an invaluable tool for anyone looking to elevate their everyday experience. Copilot Vision is a new AI feature within Microsoft Edge that provides real-time assistance as you browse the web. It scans the web page you’re on, analyzes the content, and offers helpful insights or guidance on tasks such as planning activities, shopping, or learning new information. This feature is built with privacy and security in mind, allowing users to opt in at any time and ensuring that all browsing data is deleted once the session ends. Initially available to a limited number of Pro subscribers, Copilot Vision is set to expand over time.

Introducing Microsoft 365 Copilot — your innovative partner in productivity. This remarkable tool harnesses the capabilities of advanced language models alongside your data from the Microsoft Graph and various Microsoft 365 applications, transforming your written input into an unparalleled productivity asset. Copilot seamlessly integrates into Microsoft 365 in two distinct manners. It collaborates with you within the familiar Microsoft 365 applications you utilize daily — including Word, Excel, PowerPoint, Outlook, Teams, and more — to stimulate creativity, enhance productivity, and elevate your skill set. Additionally, we are excited to unveil a completely new feature: Business Chat. This feature operates across the advanced language model, the suite of Microsoft 365 apps, and your personal data — encompassing your calendar, emails, chats, documents, meetings, and contacts — enabling you to accomplish tasks previously thought impossible. You can interact with it using natural language commands, such as “Update my team on the changes made to the product strategy,” and it will create a comprehensive status report synthesizing information from the morning’s meetings, emails, and chat discussions. With these advancements, the potential for streamlined communication and collaboration has never been greater.

Grok-3, created by xAI, signifies a major leap forward in artificial intelligence technology, with aspirations to establish new standards in AI performance. This model is engineered as a multimodal AI, enabling it to interpret and analyze information from diverse channels such as text, images, and audio, thereby facilitating a more holistic interaction experience for users. Grok-3 is constructed on an unprecedented scale, utilizing tenfold the computational resources of its predecessor, harnessing the power of 100,000 Nvidia H100 GPUs within the Colossus supercomputer. Such remarkable computational capabilities are expected to significantly boost Grok-3's effectiveness across various domains, including reasoning, coding, and the real-time analysis of ongoing events by directly referencing X posts. With these advancements, Grok-3 is poised to not only surpass its previous iterations but also rival other prominent AI systems in the generative AI ecosystem, potentially reshaping user expectations and capabilities in the field. The implications of Grok-3's performance could redefine how AI is integrated into everyday applications, paving the way for more sophisticated technological solutions.

The Model Context Protocol (MCP) is a flexible, open-source framework that streamlines the interaction between AI models and external data sources. It enables developers to create complex workflows by connecting LLMs with databases, files, and web services, offering a standardized approach for AI applications. MCP’s client-server architecture ensures seamless integration, while its growing list of integrations makes it easy to connect with different LLM providers. The protocol is ideal for those looking to build scalable AI agents with strong data security practices.

GPT-4.1 represents a significant upgrade in generative AI, with notable advancements in coding, instruction adherence, and handling long contexts. This model supports up to 1 million tokens of context, allowing it to tackle complex, multi-step tasks across various domains. GPT-4.1 outperforms earlier models in key benchmarks, particularly in coding accuracy, and is designed to streamline workflows for developers and businesses by improving task completion speed and reliability.

Claude Opus 4 is the pinnacle of AI coding models, leading the way in software engineering tasks with an impressive SWE-bench score of 72.5% and Terminal-bench score of 43.2%. Its ability to handle complex challenges, large codebases, and multiple files simultaneously sets it apart from all other models. Opus 4 excels at coding tasks that require extended focus and problem-solving, automating tasks for software developers, engineers, and data scientists. This AI model doesn’t just perform—it continuously improves its capabilities over time, handling real-world challenges and optimizing workflows with confidence. Available through multiple platforms like Anthropic API, Amazon Bedrock, and Gemini Enterprise Agent Platform, Opus 4 is a must-have for cutting-edge developers and businesses looking to stay ahead.

Claude Opus 4.7 is an advanced AI model built to push the boundaries of software engineering, automation, and complex reasoning tasks. Compared to Opus 4.6, it delivers notable improvements in handling challenging coding workflows and executing long-duration tasks with consistency. The model excels at strictly following user instructions, reducing ambiguity and improving output accuracy. It also introduces stronger self-verification capabilities, allowing it to check and refine its own results before presenting them. One of its key upgrades is enhanced multimodal functionality, particularly its ability to process higher-resolution images with greater clarity. This enables more precise analysis of visuals such as technical diagrams, dense screenshots, and structured data layouts. Opus 4.7 is also more refined in generating professional content, including polished documents, presentations, and interface designs. In real-world applications, it performs effectively across domains like finance, legal analysis, and business workflows. The model incorporates improved memory features, allowing it to retain context across extended sessions and reduce repetitive input requirements. It also introduces built-in safeguards to detect and prevent misuse, especially in sensitive cybersecurity scenarios. With broad availability across APIs and cloud platforms, Opus 4.7 offers developers and enterprises a powerful, scalable AI solution.

MAI-Image-2.5-Flash is an innovative model developed within Microsoft Foundry that specializes in transforming text prompts into stunning images and allows for detailed editing of existing visuals. Utilizing a diffusion-based generative technique, it incrementally enhances images to achieve a seamless correlation between the provided text and the resulting visuals. This model is designed for dynamic workflows, enabling users to articulate their creative visions, tailor current images, or produce high-quality creative assets with enhanced control over artistic elements and layout. As a component of Microsoft's MAI image generation suite, MAI-Image-2.5-Flash is optimized for rapid and scalable image creation and modification, making it ideal for both enterprise and developer applications, accessible via the Microsoft Foundry model catalog. It caters specifically to scenarios that require visual content generation within business applications, creative software, and content production processes, ensuring versatility and efficiency. Additionally, this model represents a significant advancement in facilitating user creativity while maintaining high-quality standards in visual output.

MAI-Image-2.5-Pro represents Microsoft AI’s most advanced image generation model, tailored specifically for projects where visual excellence, precision, and control are essential. This innovative model produces stunning, photorealistic images that are ready for design applications, transforming basic text descriptions or uploaded images into high-quality visuals featuring realistic lighting, true-to-life skin tones, and intricate material textures ideal for professional use. It excels in creating standout imagery for branding, product representation, commercial design, and other tasks that necessitate a refined finish with minimal need for post-editing. Users benefit from its sophisticated editing tools, enabling them to implement changes through natural language while maintaining the image's overall coherence, layout, and composition, as well as allowing for seamless adjustments of objects or settings in context. Additionally, MAI-Image-2.5-Pro boasts exceptional object consistency, enhanced visual reasoning, and a greater understanding of the world, ensuring that both edits and new creations remain logically consistent, even within intricate scenes. This model not only enhances creative workflows but also empowers professionals to achieve their vision with greater ease and accuracy.

GPT-6.1 Sol is an upgraded OpenAI model that combines advanced intelligence with lower operating costs for coding, professional knowledge work, computer use, scientific research, and autonomous agents. OpenAI positions it as offering near-GPT-6 Astra intelligence at one-fifth of Astra's standard input and output token prices. The model delivers substantial improvements over GPT-6 Sol in software engineering, complex document understanding, business automation, and long-horizon computer-use workflows. On DeepSWE v1.1, GPT-6.1 Sol matches GPT-6 Astra at approximately one-fifth of the cost and surpasses GPT-6 Sol's highest score by 6.4 percentage points at lower reasoning effort. On AutomationBench, it scores 4.8 percentage points higher than GPT-6 Sol at the same reasoning setting and 2.2 points above Opus 5.5 at medium reasoning effort. GPT-6.1 Sol also improves computer use, coming within 2.1 percentage points of GPT-6 Astra on the OSWorld 2.0 offline set at maximum reasoning effort while costing roughly one-seventh as much per task. For scientific workflows, the model more than doubles GPT-6 Sol's Terminal-Bench Science 0.1 score at maximum effort while reducing average task cost by more than half. Factuality has also improved, with the share of responses containing a factual error at low reasoning effort falling from 11.4% with GPT-6 Sol to 7.7% with GPT-6.1 Sol on OpenAI's difficult error-focused evaluation. Developers can access GPT-6.1 Sol through the OpenAI API for $2 per million input tokens, $0.10 per million cached input tokens, and $10 per million output tokens, while eligible users can access it through ChatGPT Work and Codex.

DeepSeek-R1 is a cutting-edge open-source reasoning model created by DeepSeek, aimed at competing with OpenAI's Model o1. It is readily available through web, app, and API interfaces, showcasing its proficiency in challenging tasks such as mathematics and coding, and achieving impressive results on assessments like the American Invitational Mathematics Examination (AIME) and MATH. Utilizing a mixture of experts (MoE) architecture, this model boasts a remarkable total of 671 billion parameters, with 37 billion parameters activated for each token, which allows for both efficient and precise reasoning abilities. As a part of DeepSeek's dedication to the progression of artificial general intelligence (AGI), the model underscores the importance of open-source innovation in this field. Furthermore, its advanced capabilities may significantly impact how we approach complex problem-solving in various domains.

Claude Sonnet 4 is an advanced AI model that enhances coding, reasoning, and problem-solving capabilities, perfect for developers and businesses in need of reliable AI support. This new version of Claude Sonnet significantly improves its predecessor’s capabilities by excelling in coding tasks and delivering precise, clear reasoning. With a 72.7% score on SWE-bench, it offers exceptional performance in software development, app creation, and problem-solving. Claude Sonnet 4’s improved handling of complex instructions and reduced errors in codebase navigation make it the go-to choice for enhancing productivity in technical workflows and software projects.

xAI’s Grok 4 represents a major step forward in AI technology, delivering advanced reasoning, multimodal understanding, and improved natural language capabilities. Built on the powerful Colossus supercomputer, Grok 4 can process text and images, with video input support expected soon, enhancing its ability to interpret cultural and contextual content such as memes. It has outperformed many competitors in benchmark tests for scientific and visual reasoning, establishing itself as a top-tier model. Focused on technical users, researchers, and developers, Grok 4 is tailored to meet the demands of advanced AI applications. xAI has strengthened moderation systems to prevent inappropriate outputs and promote ethical AI use. This release signals xAI’s commitment to innovation and responsible AI deployment. Grok 4 sets a new standard in AI performance and versatility. It is poised to support cutting-edge research and complex problem-solving across various fields.

Grok 4.1 Fast represents xAI’s leap forward in building highly capable agents that rely heavily on tool calling, long-context reasoning, and real-time information retrieval. It supports a robust 2-million-token window, enabling long-form planning, deep research, and multi-step workflows without degradation. Through extensive RL training and exposure to diverse tool ecosystems, the model performs exceptionally well on demanding benchmarks like τ²-bench Telecom. When paired with the Agent Tools API, it can autonomously browse the web, search X posts, execute Python code, and retrieve documents, eliminating the need for developers to manage external infrastructure. It is engineered to maintain intelligence across multi-turn conversations, making it ideal for enterprise tasks that require continuous context. Its benchmark accuracy on tool-calling and function-calling tasks clearly surpasses competing models in speed, cost, and reliability. Developers can leverage these strengths to build agents that automate customer support, perform real-time analysis, and execute complex domain-specific tasks. With its performance, low pricing, and availability on platforms like OpenRouter, Grok 4.1 Fast stands out as a production-ready solution for next-generation AI systems.

Claude Opus 4.6 is a state-of-the-art AI model from Anthropic, designed to deliver advanced reasoning, coding, and enterprise-level performance. It improves significantly on previous versions with better planning, debugging, and code review capabilities. The model can sustain long-running, agentic workflows and operate effectively across large codebases. One of its key features is a 1 million token context window in beta, allowing it to handle extensive documents and complex tasks. Claude Opus 4.6 excels in knowledge work, including financial analysis, research, and document creation. It also performs strongly on industry benchmarks, leading in areas like agentic coding and multidisciplinary reasoning. The model includes adaptive thinking, enabling it to adjust its reasoning depth based on task complexity. Developers can control performance using adjustable effort levels for speed, cost, and accuracy. It integrates with productivity tools such as Excel and PowerPoint for enhanced workflow automation. Overall, Claude Opus 4.6 provides a powerful and reliable AI solution for professional and enterprise use cases.

MAI-Code-1-Flash is an innovative coding model developed by Microsoft, aimed at providing quick and effective support for developers in their daily tasks. This model, which has been meticulously created using clean and properly licensed data, is being introduced to GitHub Copilot individual users within Visual Studio Code via the model picker and the default Auto picker. Its primary objective is to enhance the quality of coding assistance while boosting efficiency, enabling engineering teams to produce superior code at a faster pace through a streamlined, agentic model seamlessly integrated into GitHub Copilot and VS Code. Notably, MAI-Code-1-Flash has been trained using GitHub Copilot production harnesses, equipping it to function in real developer settings and interact with various tools and systems rather than being solely fine-tuned for static benchmarks. The model excels in agentic coding, robust instruction-following across both single-turn and multi-turn interactions, answering questions related to repositories, performing refactoring, tackling telemetry-driven tasks, and showcasing adaptive thinking capabilities. In summary, this model represents a significant advancement in coding assistance technology, promising to transform how developers engage with their coding environments.

MAI-Code-1.1-Flash is a compact and effective coding model aimed at enhancing the speed and quality of code development for engineering teams. Currently implemented in GitHub Copilot and integrated into VS Code, it caters to the actual workflows of developers, specifically enhancing command-line operations and .NET tasks based on user input. When compared to the version unveiled at Microsoft Build in June, this model showcases a significant improvement in code quality, achieved with reduced token usage and quicker streaming responses. Microsoft claims a 22% enhancement on Terminal-Bench 2.1 for GitHub Copilot CLI and a 15% boost in .NET task performance. Additionally, production outcomes indicate a 4% rise in code survival rates and a 9% increase in users returning to the platform. Notably, in GitHub Copilot, tokens are streamed 25% faster, and the model requires 25% fewer tokens for task completion, which translates to quicker responses, reduced wait times, and enhanced productivity from each token processed. These advancements stem from refined training methods and improved operational efficiencies, with a strong focus on practical application in real-world scenarios. Ultimately, MAI-Code-1.1-Flash represents a significant leap forward in coding assistance technology.

GPT-5.1 Pro is a premium, research-focused model tier built for users who need the strongest reasoning performance ChatGPT offers. It excels in technical domains such as advanced mathematics, scientific analysis, engineering, complex coding, and financial modeling. The model is engineered to deliver more coherent long-form reasoning, better chain-of-thought structure, and stronger factual grounding than general-purpose versions. With expanded context capacity, GPT-5.1 Pro handles large documents, multi-file analysis, and intricate workflows with ease. It also produces clearer explanations with reduced jargon, making complex insights more accessible without losing technical depth. Designed for demanding professional environments, Pro adheres to strict accuracy expectations while minimizing hallucinations in critical tasks. It is restricted to ChatGPT Pro and Business plans, ensuring dedicated access with no usage caps beyond standard abuse guardrails. Compared to other tiers, GPT-5.1 Pro is purpose-built for users who rely on ChatGPT as a high-precision analytical engine.

Claude Sonnet 4.6 represents a comprehensive upgrade to Anthropic’s Sonnet model line, delivering expanded capabilities across coding, reasoning, computer interaction, and professional knowledge tasks. With a beta 1M token context window, the model can process massive datasets such as full repositories, extended legal agreements, or multi-document research projects in a single request. Developers report improved reliability, better instruction adherence, and fewer hallucinations, making long working sessions smoother and more predictable. Early users preferred Sonnet 4.6 over its predecessor in the majority of tests and often selected it over Opus 4.5 for practical coding work. The model’s computer-use skills have advanced significantly, enabling it to navigate spreadsheets, complete web forms, and manage multi-tab workflows with near human-level competence in many cases. Benchmark evaluations show consistent performance gains across reasoning, coding, and long-horizon planning tasks. In competitive simulations like Vending-Bench Arena, Sonnet 4.6 demonstrated strategic capacity-building and profit optimization over time. On the developer platform, it supports adaptive and extended thinking modes, context compaction, and improved tool integration for greater efficiency. Claude’s API tools now automatically execute filtering and code-processing steps to enhance search and token optimization. Sonnet 4.6 is available across Claude.ai, Cowork, Claude Code, the API, and major cloud providers at the same starting price as Sonnet 4.5.

Grok 4.3 is an advanced AI model developed by xAI to provide enhanced reasoning, real-time insights, and automation capabilities. It builds on the Grok 4 architecture, which already includes features like real-time web browsing, multimodal processing, and tool integration. The model is designed to handle complex tasks such as coding, research, and data analysis with improved accuracy and efficiency. Grok 4.3 is integrated with live data sources, including the web and X, allowing it to deliver timely and relevant information. It operates within the SuperGrok Heavy subscription tier, which provides access to its most powerful capabilities. The model supports long-context understanding, enabling it to process large amounts of information in a single session. It also includes multi-agent or “heavy” configurations that enhance problem-solving performance. Grok 4.3 is optimized for speed and responsiveness, making it suitable for real-time applications. It can generate content, answer questions, and assist with workflows across various domains. The platform continues to evolve with new features and improvements aimed at increasing reliability and performance. Overall, Grok 4.3 offers a powerful AI solution for users who need real-time, high-level intelligence and automation.

Microsoft Copilot Studio is a powerful and flexible platform designed to help users create, customize, and manage AI-driven agents tailored to meet diverse business needs. Combining the simplicity of low-code development with the advanced capabilities of generative AI, the platform enables users to design intelligent agents that can access and utilize internal knowledge bases, perform complex actions through a wide range of data connectors, and operate autonomously to streamline processes and improve productivity. These AI agents can be seamlessly integrated into existing workflows and deployed across various channels, including Microsoft 365 applications, internal websites, and mobile apps, ensuring they adapt to the unique operational environments of any organization. Furthermore, Copilot Studio includes a robust suite of governance and management tools, allowing IT teams to maintain centralized control over agent usage, monitor performance with detailed analytics, and enforce security policies. This combination of ease of use, advanced functionality, and comprehensive governance makes Microsoft Copilot Studio an invaluable tool for organizations looking to leverage AI to transform their business operations.

Microsoft Purview serves as a comprehensive data governance platform that facilitates the management and oversight of your data across on-premises, multicloud, and software-as-a-service (SaaS) environments. With its capabilities in automated data discovery, sensitive data classification, and complete data lineage tracking, you can effortlessly develop a thorough and current representation of your data ecosystem. This empowers data users to access reliable and valuable data easily. The service provides automated identification of data lineage and classification across various sources, ensuring a cohesive view of your data assets and their interconnections for enhanced governance. Through semantic search, users can discover data using both business and technical terminology, providing insights into the location and flow of sensitive information within a hybrid data environment. By leveraging the Purview Data Map, you can lay the groundwork for effective data utilization and governance, while also automating and managing metadata from diverse sources. Additionally, it supports the classification of data using both predefined and custom classifiers, along with Microsoft Information Protection sensitivity labels, ensuring that your data governance framework is robust and adaptable. This combination of features positions Microsoft Purview as an essential tool for organizations seeking to optimize their data management strategies.

Connecting every data source with analytics services on a single AI-powered platform will transform how people access, manage, and act on data and insights. All your data. All your teams. All your teams in one place. Create an open, lake-centric hub to help data engineers connect data from various sources and curate it. This will eliminate sprawl and create custom views for all. Accelerate analysis through the development of AI models without moving data. This reduces the time needed by data scientists to deliver value. Microsoft Teams, Microsoft Excel, and Microsoft Teams are all great tools to help your team innovate faster. Connect people and data responsibly with an open, scalable solution. This solution gives data stewards more control, thanks to its built-in security, compliance, and governance.

Mistral AI has introduced the Mistral Large 2, a sophisticated AI model crafted to excel in various domains such as code generation, multilingual understanding, and intricate reasoning tasks. With an impressive 128k context window, this model accommodates a wide array of languages, including English, French, Spanish, and Arabic, while also supporting an extensive list of over 80 programming languages. Designed for high-throughput single-node inference, Mistral Large 2 is perfectly suited for applications requiring large context handling. Its superior performance on benchmarks like MMLU, coupled with improved capabilities in code generation and reasoning, guarantees both accuracy and efficiency in results. Additionally, the model features enhanced function calling and retrieval mechanisms, which are particularly beneficial for complex business applications. This makes Mistral Large 2 not only versatile but also a powerful tool for developers and businesses looking to leverage advanced AI capabilities.

Mistral Small 3.1 represents a cutting-edge, multimodal, and multilingual AI model that has been released under the Apache 2.0 license. This upgraded version builds on Mistral Small 3, featuring enhanced text capabilities and superior multimodal comprehension, while also accommodating an extended context window of up to 128,000 tokens. It demonstrates superior performance compared to similar models such as Gemma 3 and GPT-4o Mini, achieving impressive inference speeds of 150 tokens per second. Tailored for adaptability, Mistral Small 3.1 shines in a variety of applications, including instruction following, conversational support, image analysis, and function execution, making it ideal for both business and consumer AI needs. The model's streamlined architecture enables it to operate efficiently on hardware such as a single RTX 4090 or a Mac equipped with 32GB of RAM, thus supporting on-device implementations. Users can download it from Hugging Face and access it through Mistral AI's developer playground, while it is also integrated into platforms like Gemini Enterprise Agent Platform, with additional accessibility on NVIDIA NIM and more. This flexibility ensures that developers can leverage its capabilities across diverse environments and applications.