{"id":613,"date":"2026-04-09T12:23:27","date_gmt":"2026-04-09T09:23:27","guid":{"rendered":"https:\/\/shareai.now\/?p=613"},"modified":"2026-04-14T03:21:12","modified_gmt":"2026-04-14T00:21:12","slug":"deepseek-v3-1-671b-finally-on-shareai","status":"publish","type":"post","link":"https:\/\/shareai.now\/blog\/news\/deepseek-v3-1-671b-finally-on-shareai\/","title":{"rendered":"DeepSeek-V3.1 671B finally on ShareAI"},"content":{"rendered":"\n<p><strong>The wait is over.<\/strong><br>Starting today, DeepSeek-V3.1 <strong>671B<\/strong> is live on ShareAI\u2014built for providers with serious infrastructure who want to deliver frontier-grade inference to their customers.<\/p>\n\n\n\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>Have a big infrastructure and want to give your clients the latest, greatest AI inference? The wait is over.<\/p>\n<\/blockquote>\n\n\n\n<h2 class=\"wp-block-heading\">Why this matters<\/h2>\n\n\n\n<p>DeepSeek-V3.1 is a <strong>hybrid model<\/strong> that supports both <strong>thinking<\/strong> and <strong>non-thinking<\/strong> modes\u2014one model, two behaviors\u2014switchable via chat template. It brings three big upgrades:<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Hybrid thinking mode<\/strong> \u2014 Toggle between thinking and non-thinking by changing the chat template.<\/li>\n\n\n\n<li><strong>Smarter tool calling<\/strong> \u2014 Post-training optimization boosts performance for tool use and agent-style tasks.<\/li>\n\n\n\n<li><strong>Higher thinking efficiency<\/strong> \u2014 DeepSeek-V3.1-Think reaches answer quality comparable to DeepSeek-R1-0528, while responding <strong>faster<\/strong>.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">What you can do now<\/h2>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>Offer frontier inference<\/strong> to enterprise clients that demand speed, scale, and reliability.<\/li>\n\n\n\n<li><strong>Run agentic workflows<\/strong> with improved tool execution and planning.<\/li>\n\n\n\n<li><strong>Choose your reasoning style<\/strong> per request: thinking on for tough problems, off for low-latency chats.<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">Getting started on ShareAI<\/h2>\n\n\n\n<ol class=\"wp-block-list\">\n<li><strong>Select the model:<\/strong> <code>deepseek-v3.1-671b<\/code>.<\/li>\n\n\n\n<li><strong>Pick the mode:<\/strong> set the chat template to <strong>Thinking<\/strong> or <strong>Standard<\/strong>.<\/li>\n\n\n\n<li><strong>Wire your tools:<\/strong> pass your function\/tool schema as usual\u2014V3.1 is optimized for it.<\/li>\n\n\n\n<li><strong>Ship:<\/strong> route traffic from your existing endpoints; monitor as you do today.<\/li>\n<\/ol>\n\n\n\n<h2 class=\"wp-block-heading\">Who is it for?<\/h2>\n\n\n\n<p>Clouds, platforms, and providers with <strong>big infra<\/strong> and bigger ambitions\u2014teams shipping next-gen assistants, research copilots, and high-throughput inference services.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Availability<\/h2>\n\n\n\n<p>DeepSeek-V3.1 671B is available <strong>today<\/strong> on ShareAI. Turn it on in your workspace or reach out for quota and SLAs.<\/p>\n\n\n\n<p><strong>Ready to build the frontier?<\/strong><br>\u2192 <em>Enable DeepSeek-V3.1<\/em> \u2022 <em>Start building<\/em> \u2022 <em>Talk to sales<\/em><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The wait is over.Starting today, DeepSeek-V3.1 671B is live on ShareAI\u2014built for providers with serious infrastructure who want to deliver frontier-grade inference to their customers. Have a big infrastructure and want to give your clients the latest, greatest AI inference? The wait is over. Why this matters DeepSeek-V3.1 is a hybrid model that supports both [&hellip;]<\/p>\n","protected":false},"author":1,"featured_media":627,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"cta-title":"","cta-description":"","cta-button-text":"","cta-button-link":"","rank_math_title":"","rank_math_description":"Hybrid thinking. Smarter tools. Faster answers. Now on ShareAI","rank_math_focus_keyword":"Deepseek-v3.1 671b,deepseek-v3.1,deepseek 3.1","footnotes":""},"categories":[7],"tags":[],"class_list":["post-613","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news"],"_links":{"self":[{"href":"https:\/\/shareai.now\/api\/wp\/v2\/posts\/613","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/shareai.now\/api\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/shareai.now\/api\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/shareai.now\/api\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/shareai.now\/api\/wp\/v2\/comments?post=613"}],"version-history":[{"count":1,"href":"https:\/\/shareai.now\/api\/wp\/v2\/posts\/613\/revisions"}],"predecessor-version":[{"id":615,"href":"https:\/\/shareai.now\/api\/wp\/v2\/posts\/613\/revisions\/615"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/shareai.now\/api\/wp\/v2\/media\/627"}],"wp:attachment":[{"href":"https:\/\/shareai.now\/api\/wp\/v2\/media?parent=613"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/shareai.now\/api\/wp\/v2\/categories?post=613"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/shareai.now\/api\/wp\/v2\/tags?post=613"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}