{"id":45753,"date":"2024-09-26T16:13:32","date_gmt":"2024-09-26T14:13:32","guid":{"rendered":"https:\/\/www.schneider.im\/?p=45753"},"modified":"2024-09-26T16:13:56","modified_gmt":"2024-09-26T14:13:56","slug":"microsoft-azure-adds-openais-o1-preview-and-o1-mini-models","status":"publish","type":"post","link":"https:\/\/www.schneider.im\/lu\/microsoft-azure-adds-openais-o1-preview-and-o1-mini-models\/","title":{"rendered":"Microsoft Azure adds OpenAI\u2019s o1-preview and o1-mini models"},"content":{"rendered":"<p style=\"text-align: justify;\">On September 12, 2024, <strong>OpenAI&#8217;s<\/strong> newest models &#8220;<strong>o1-preview<\/strong>&#8221; and &#8220;<strong>o1-mini<\/strong>&#8221; were introduced. <strong>Soon,<\/strong> these <strong>models<\/strong> will <strong>join Microsoft Azure OpenAI Service, Azure AI Studio, and GitHub Models<\/strong>.<\/p>\n<p style=\"text-align: justify;\"><img decoding=\"async\" class=\"size-full wp-image-45766 aligncenter\" src=\"https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-26-Update-Website-Microsoft-Azure-OpenAI-o1.png\" alt=\"\" width=\"800\" height=\"514\" srcset=\"https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-26-Update-Website-Microsoft-Azure-OpenAI-o1.png 800w, https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-26-Update-Website-Microsoft-Azure-OpenAI-o1-300x193.png 300w, https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-26-Update-Website-Microsoft-Azure-OpenAI-o1-150x96.png 150w, https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-26-Update-Website-Microsoft-Azure-OpenAI-o1-768x493.png 768w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2 style=\"text-align: justify;\"><strong>What are OpenAI o1-preview and o1-mini models?<\/strong><\/h2>\n<p style=\"text-align: justify;\">The OpenAI o1-preview and o1-mini models are specifically designed to tackle <strong>reasoning and problem-solving tasks<\/strong> with increased focus and capability. These models <strong>spend more time processing and understanding the user&#8217;s request<\/strong>. This makes them exceptionally strong in areas like science, coding, and math.<\/p>\n<ul style=\"text-align: justify;\">\n<li><strong>o1-preview<\/strong>: Designed for advanced reasoning and solving complex problems, including math and science tasks. Ideal for applications requiring deep contextual understanding and agentic workflows.<\/li>\n<li><strong>o1-mini<\/strong>: A smaller, faster, and 80% cheaper model compared to o1-preview. It excels in code generation and small context operations.<\/li>\n<\/ul>\n<p style=\"text-align: justify;\"><img decoding=\"async\" class=\"size-large wp-image-45754 aligncenter\" src=\"https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-24-Update-Website-Microsoft-Azure-OpenAI-o1-models-GitHub-800x489.webp\" alt=\"\" width=\"800\" height=\"489\" srcset=\"https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-24-Update-Website-Microsoft-Azure-OpenAI-o1-models-GitHub-800x489.webp 800w, https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-24-Update-Website-Microsoft-Azure-OpenAI-o1-models-GitHub-300x183.webp 300w, https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-24-Update-Website-Microsoft-Azure-OpenAI-o1-models-GitHub-150x92.webp 150w, https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-24-Update-Website-Microsoft-Azure-OpenAI-o1-models-GitHub-768x470.webp 768w, https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-24-Update-Website-Microsoft-Azure-OpenAI-o1-models-GitHub-1536x939.webp 1536w, https:\/\/www.schneider.im\/media\/2024\/09\/SCHNEIDER-IT-MANAGEMENT-2024-09-24-Update-Website-Microsoft-Azure-OpenAI-o1-models-GitHub.webp 1616w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2 style=\"text-align: justify;\"><strong>Key capabilities of the OpenAI o1 series<\/strong><\/h2>\n<ul style=\"text-align: justify;\">\n<li><strong>Complex Code Generation<\/strong>: Capable of generating algorithms and handling advanced coding tasks to support developers.<\/li>\n<li><strong>Advanced Problem Solving<\/strong>: Ideal for comprehensive brainstorming sessions and addressing multifaceted challenges.<\/li>\n<li><strong>Complex Document Comparison<\/strong>: Perfect for analyzing contracts, case files, or legal documents to identify subtle differences.<\/li>\n<li><strong>Instruction Following and Workflow Management<\/strong>: Particularly effective for managing workflows requiring shorter contexts.<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h2 style=\"text-align: justify;\"><strong>Use Cases<\/strong><\/h2>\n<p style=\"text-align: justify;\">For example, o1 can be used by <strong>healthcare<\/strong> <strong>researchers<\/strong> to annotate cell sequencing data. It can help <strong>physicists<\/strong> to generate complicated mathematical formulas needed for quantum optics. It is also interesting for <strong>developers<\/strong> wanting to build and execute multi-step workflows.<\/p>\n<p>&nbsp;<\/p>\n<h2 style=\"text-align: justify;\"><strong>Current Limitations<\/strong><\/h2>\n<p style=\"text-align: justify;\">o1-preview and o1-mini <strong>do not allow web browsing, file uploads or structured outputs<\/strong> which are available in the latest GPT-4o model. These features will follow soon for ChatGPT and Azure. For many common tasks, GPT-4o remains more capable in the near term. However, for complex reasoning tasks, the o1 series represents a significant advancement.<\/p>\n<p>&nbsp;<\/p>\n<h2 style=\"text-align: justify;\"><strong>Comparing GPT-4o, o1-mini and o1-preview<\/strong><\/h2>\n<p style=\"text-align: justify;\">The new o1 models excel in challenging tasks. The chart below compares the test results of GPT-4o, o1-mini, and o1-preview across various <strong>coding and Science, Technology, Engineering, and Mathematics (STEM) tests<\/strong>. A wider bar indicates better performance compared to the other models.<\/p>\n<p style=\"text-align: justify;\"><img decoding=\"async\" class=\"size-large wp-image-45758 aligncenter\" src=\"https:\/\/www.schneider.im\/media\/2024\/09\/OpenAI-model-comparison-800x242.png\" alt=\"\" width=\"800\" height=\"242\" srcset=\"https:\/\/www.schneider.im\/media\/2024\/09\/OpenAI-model-comparison-800x242.png 800w, https:\/\/www.schneider.im\/media\/2024\/09\/OpenAI-model-comparison-300x91.png 300w, https:\/\/www.schneider.im\/media\/2024\/09\/OpenAI-model-comparison-150x45.png 150w, https:\/\/www.schneider.im\/media\/2024\/09\/OpenAI-model-comparison-768x232.png 768w, https:\/\/www.schneider.im\/media\/2024\/09\/OpenAI-model-comparison.png 1525w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/><\/p>\n<p>&nbsp;<\/p>\n<h2 style=\"text-align: justify;\"><strong>Availability via Azure<\/strong><\/h2>\n<p style=\"text-align: justify;\"><img decoding=\"async\" class=\"size-large wp-image-45762 aligncenter\" src=\"https:\/\/www.schneider.im\/media\/2024\/09\/Microsoft-Azure-OpenAI-o1-800x226.png\" alt=\"\" width=\"800\" height=\"226\" srcset=\"https:\/\/www.schneider.im\/media\/2024\/09\/Microsoft-Azure-OpenAI-o1-800x226.png 800w, https:\/\/www.schneider.im\/media\/2024\/09\/Microsoft-Azure-OpenAI-o1-300x85.png 300w, https:\/\/www.schneider.im\/media\/2024\/09\/Microsoft-Azure-OpenAI-o1-150x42.png 150w, https:\/\/www.schneider.im\/media\/2024\/09\/Microsoft-Azure-OpenAI-o1-768x217.png 768w, https:\/\/www.schneider.im\/media\/2024\/09\/Microsoft-Azure-OpenAI-o1.png 1537w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/><\/p>\n<p style=\"text-align: justify;\">We <strong>expect<\/strong> them to become <strong>generally available in the coming weeks in Azure<\/strong>.<\/p>\n<p>&nbsp;<\/p>\n<h2 style=\"text-align: justify;\"><strong>Security<\/strong><\/h2>\n<p style=\"text-align: justify;\">o1-preview and o1-mini models in Azure OpenAI Service have <strong>Content Safety features activated by default<\/strong>, at <strong>no additional cost<\/strong> for customers.<\/p>\n<p>&nbsp;<\/p>\n<h2 style=\"text-align: justify;\"><strong>FAQ<\/strong><\/h2>\n<h3 style=\"text-align: justify;\">What are the main differences between o1-preview and o1-mini?<\/h3>\n<p style=\"text-align: justify;\">o1-preview is focused on advanced reasoning and solving complex problems, while o1-mini is smaller, faster, and more cost-effective and excels in code generation and small context operations.<\/p>\n<h3 style=\"text-align: justify;\">What are the key applications of these models?<\/h3>\n<p style=\"text-align: justify;\">The o1 series is ideal for complex coding, math reasoning, brainstorming, and comparative analysis. They are particularly useful for advanced problem-solving and document comparison.<\/p>\n<h3 style=\"text-align: justify;\">Is there any way to try them already?<\/h3>\n<p style=\"text-align: justify;\">Yes. OpenAI is planning to bring o1-mini access to all ChatGPT Free users so you can try it out in ChatGPT (without data protection!).<\/p>\n<p>&nbsp;<\/p>\n<h2 style=\"text-align: justify;\"><strong>More information<\/strong><\/h2>\n<p style=\"text-align: justify;\">The <strong>announcement<\/strong> can be found here: <a href=\"https:\/\/azure.microsoft.com\/en-us\/blog\/introducing-o1-openais-new-reasoning-model-series-for-developers-and-enterprises-on-azure\/\">https:\/\/azure.microsoft.com\/en-us\/blog\/introducing-o1-openais-new-reasoning-model-series-for-developers-and-enterprises-on-azure\/<\/a>.<\/p>\n<p style=\"text-align: justify;\">Access <strong>o1-preview on Azure<\/strong>: <a href=\"https:\/\/ai.azure.com\/explore\/models\/o1-preview\/version\/1\/registry\/azure-openai\">https:\/\/ai.azure.com\/explore\/models\/o1-preview\/version\/1\/registry\/azure-openai<\/a>.<\/p>\n<p style=\"text-align: justify;\">Access <strong>o1-mini on Azure<\/strong>: <a href=\"https:\/\/ai.azure.com\/explore\/models\/o1-mini\/version\/1\/registry\/azure-openai\">https:\/\/ai.azure.com\/explore\/models\/o1-mini\/version\/1\/registry\/azure-openai<\/a>.<\/p>\n<p style=\"text-align: justify;\">Find an <strong>article<\/strong> on <strong>reasoning with OpenAI o1<\/strong> here: <a href=\"https:\/\/openai.com\/index\/learning-to-reason-with-llms\/\">https:\/\/openai.com\/index\/learning-to-reason-with-llms\/<\/a>.<\/p>\n<p style=\"text-align: justify;\">To learn about <strong>Microsoft Licensing with SCHNEIDER IT MANAGEMENT<\/strong>, please visit: <a href=\"https:\/\/www.schneider.im\/software\/microsoft\/\">https:\/\/www.schneider.im\/software\/microsoft<\/a>.<\/p>\n<p style=\"text-align: justify;\">Please <a href=\"https:\/\/www.schneider.im\/contact\/\">contact us<\/a> for <strong>expert services<\/strong> on your specific Microsoft software and online services requirements and to <strong>request a quote today<\/strong>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>On September 12, 2024, OpenAI&#8217;s newest models &#8220;o1-preview&#8221; and &#8220;o1-mini&#8221; were introduced. Soon, these models will join Microsoft Azure OpenAI Service, Azure AI Studio, and GitHub Models. &nbsp; What are OpenAI o1-preview and o1-mini models? The OpenAI o1-preview and o1-mini models are specifically designed to tackle reasoning and problem-solving tasks with increased focus and capability. [&hellip;]<\/p>\n","protected":false},"author":11,"featured_media":33016,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[248],"tags":[],"class_list":["post-45753","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-microsoft-azure"],"_links":{"self":[{"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/posts\/45753","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/users\/11"}],"replies":[{"embeddable":true,"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/comments?post=45753"}],"version-history":[{"count":2,"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/posts\/45753\/revisions"}],"predecessor-version":[{"id":45771,"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/posts\/45753\/revisions\/45771"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/media\/33016"}],"wp:attachment":[{"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/media?parent=45753"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/categories?post=45753"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.schneider.im\/lu\/wp-json\/wp\/v2\/tags?post=45753"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}