mirror of
https://github.com/zenlm/zen-blog.git
synced 2026-11-02 17:28:53 +00:00
Root cause of HF + GitHub + section icons not appearing in the docs route: Next.js React hydration was stripping the inline <script> + <style> elements I'd injected into <body> on every docs page during DOM reconciliation. The script never registered its setInterval. Move the decorator to /zen-decorate.js loaded via <script defer src> in <head>. React leaves external <script src> elements alone, so the intervals stay alive. The keyframes CSS is now also small enough to stay in <body> (React will strip it but the @keyframes are already registered in the global CSSOM by the time it does).
133 lines
43 KiB
HTML
133 lines
43 KiB
HTML
<!DOCTYPE html><!--i_dnJM_MIpJSOCQWNJVMq--><html lang="en" class="dark"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="stylesheet" href="/_next/static/chunks/f2332aac77592f9d.css" data-precedence="next"/><link rel="preload" as="script" fetchPriority="low" href="/_next/static/chunks/e83606e8fa9cc796.js"/><script src="/_next/static/chunks/36d6595f0156cd7e.js" async=""></script><script src="/_next/static/chunks/040e9cea20a8d9c7.js" async=""></script><script src="/_next/static/chunks/d4dffb5a0973d49c.js" async=""></script><script src="/_next/static/chunks/turbopack-967f27a9fd33556d.js" async=""></script><script src="/_next/static/chunks/59d0ad1b64f8544e.js" async=""></script><script src="/_next/static/chunks/4d80e004cf4896dd.js" async=""></script><script src="/_next/static/chunks/350ee4303b732916.js" async=""></script><script src="/_next/static/chunks/8de849ca74fc071f.js" async=""></script><script src="/_next/static/chunks/e62b91212ee7f8ff.js" async=""></script><script src="/_next/static/chunks/f19fe44237e54646.js" async=""></script><script src="/_next/static/chunks/cb0a883bafeb6805.js" async=""></script><meta name="theme-color" media="(prefers-color-scheme: dark)" content="#0A0A0A"/><meta name="theme-color" media="(prefers-color-scheme: light)" content="#fff"/><title>Introducing Zen 5 — Our Most Capable Model Yet — Zen LM Blog | Zen LM</title><meta name="description" content="Zen 5 brings 1T+ parameter scale, 2M context windows, and state-of-the-art performance across reasoning, code, and multimodal tasks."/><meta property="og:title" content="Zen LM - Open Foundation Models"/><meta property="og:description" content="Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."/><meta property="og:url" content="https://zenlm.org"/><meta property="og:site_name" content="Zen LM"/><meta property="og:type" content="website"/><meta name="twitter:card" content="summary_large_image"/><meta name="twitter:site" content="@zenlmorg"/><meta name="twitter:creator" content="@zenlmorg"/><meta name="twitter:title" content="Zen LM - Open Foundation Models"/><meta name="twitter:description" content="Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks."/><script src="/_next/static/chunks/a6dad97d9634a72d.js" noModule=""></script><script defer src="/zen-decorate.js"></script></head><body class="antialiased"><div hidden=""><!--$--><!--/$--></div><script>((a,b,c,d,e,f,g,h)=>{let i=document.documentElement,j=["light","dark"];function k(b){var c;(Array.isArray(a)?a:[a]).forEach(a=>{let c="class"===a,d=c&&f?e.map(a=>f[a]||a):e;c?(i.classList.remove(...d),i.classList.add(f&&f[b]?f[b]:b)):i.setAttribute(a,b)}),c=b,h&&j.includes(c)&&(i.style.colorScheme=c)}if(d)k(d);else try{let a=localStorage.getItem(b)||c,d=g&&"system"===a?window.matchMedia("(prefers-color-scheme: dark)").matches?"dark":"light":a;k(d)}catch(a){}})("class","theme","system",null,["light","dark"],null,true,true)</script><!--$--><div data-closed="" role="presentation" hidden="" style="user-select:none;-webkit-user-select:none" class="fixed inset-0 z-50 backdrop-blur-xs bg-fd-overlay data-open:animate-fd-fade-in data-closed:animate-fd-fade-out"></div><div class="bg-fd-secondary/50 p-3 empty:hidden"></div><!--/$--><main class="mx-auto w-full max-w-2xl px-4 py-16"><a class="inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors" href="/blog">← Back to Blog</a><div class="mb-8"><time class="text-xs font-mono text-fd-muted-foreground uppercase tracking-wider">February 28, 2026</time><h1 class="text-3xl font-bold mt-2 mb-3">Introducing Zen 5 — Our Most Capable Model Yet</h1><p class="text-fd-muted-foreground text-lg mb-4">Zen 5 brings 1T+ parameter scale, 2M context windows, and state-of-the-art performance across reasoning, code, and multimodal tasks.</p><div class="flex items-center gap-3 pt-4 border-t border-fd-border"><span class="text-sm text-fd-muted-foreground">By <!-- -->Zen LM Team</span><div class="flex gap-1.5 ml-auto"><span class="text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded">release</span><span class="text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded">zen5</span><span class="text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded">flagship</span></div></div></div><div class="prose dark:prose-invert max-w-none"><p>We're thrilled to announce the <strong>Zen 5</strong> family — our most capable generation of foundation models, pushing the frontier of what open models can achieve.</p>
|
|
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="whats-new-in-zen-5"><a data-card="" href="#whats-new-in-zen-5" class="peer">What's New in Zen 5</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
|
<p>Zen 5 represents a major leap forward across every dimension that matters:</p>
|
|
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="scale-and-architecture"><a data-card="" href="#scale-and-architecture" class="peer">Scale and Architecture</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
|
|
<p>Zen 5 is built on the <strong>Zen MoDE</strong> (Mixture of Distilled Experts) architecture — a framework that combines the best of sparse expert routing with distillation from multiple frontier models. At 1T+ total parameters with intelligent expert activation, Zen 5 achieves flagship intelligence without the inference cost of a dense trillion-parameter model.</p>
|
|
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="2m-context-window"><a data-card="" href="#2m-context-window" class="peer">2M Context Window</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
|
|
<p>Zen 5 supports <strong>2 million tokens</strong> of context — enough to process entire codebases, multi-hour transcripts, or hundreds of research papers in a single request. This unlocks agentic workflows that simply weren't possible before.</p>
|
|
<h3 class="flex scroll-m-28 flex-row items-center gap-2" id="the-zen-5-family"><a data-card="" href="#the-zen-5-family" class="peer">The Zen 5 Family</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h3>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div class="relative overflow-auto prose-no-margin my-6"><table><thead><tr><th>Model</th><th>Parameters</th><th>Context</th><th>Strengths</th></tr></thead><tbody><tr><td>zen5</td><td>1T+ MoE</td><td>2M</td><td>Flagship reasoning, all tasks</td></tr><tr><td>zen5-pro</td><td>480B MoE</td><td>512K</td><td>High capability, cost-efficient</td></tr><tr><td>zen5-ultra</td><td>1T+ MoE</td><td>2M</td><td>Maximum reasoning depth</td></tr><tr><td>zen5-mini</td><td>14B</td><td>128K</td><td>Fast, lightweight inference</td></tr><tr><td>zen5-max</td><td>1T+ MoE</td><td>2M</td><td>Enterprise scale</td></tr><tr><td>zen5-coder</td><td>1T+ MoE</td><td>2M</td><td>Code generation, software engineering</td></tr></tbody></table></div>
|
|
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="benchmark-performance"><a data-card="" href="#benchmark-performance" class="peer">Benchmark Performance</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
|
<p>Zen 5 achieves state-of-the-art results on major benchmarks:</p>
|
|
<ul>
|
|
<li><strong>MMLU</strong>: 92.1% (5-shot)</li>
|
|
<li><strong>HumanEval</strong>: 96.3% (pass@1)</li>
|
|
<li><strong>MATH</strong>: 91.7%</li>
|
|
<li><strong>GPQA Diamond</strong>: 75.2%</li>
|
|
</ul>
|
|
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="open-weights"><a data-card="" href="#open-weights" class="peer">Open Weights</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
|
<p>True to our commitment to open AI, Zen 5 weights are available on <a href="https://huggingface.co/zenlm/zen5" rel="noreferrer noopener" target="_blank">HuggingFace</a> under the Zen Open License. The model runs efficiently in 4-bit quantization on consumer hardware using our optimized inference stack.</p>
|
|
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="getting-started"><a data-card="" href="#getting-started" class="peer">Getting Started</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
|
<figure dir="ltr" class="my-4 bg-fd-card rounded-xl shiki relative border shadow-sm not-prose overflow-hidden text-sm shiki shiki-themes github-light github-dark" style="--shiki-light:#24292e;--shiki-dark:#e1e4e8;--shiki-light-bg:#fff;--shiki-dark-bg:#24292e" tabindex="-1"><div class="empty:hidden absolute top-3 right-2 z-2 backdrop-blur-lg rounded-lg text-fd-muted-foreground"><button type="button" class="inline-flex items-center justify-center rounded-md text-sm font-medium transition-colors duration-100 disabled:pointer-events-none disabled:opacity-50 focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-fd-ring p-1 [&_svg]:size-4 hover:text-fd-accent-foreground data-checked:text-fd-accent-foreground" aria-label="Copy Text"><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-clipboard" aria-hidden="true"><rect width="8" height="4" x="8" y="2" rx="1" ry="1"></rect><path d="M16 4h2a2 2 0 0 1 2 2v14a2 2 0 0 1-2 2H6a2 2 0 0 1-2-2V6a2 2 0 0 1 2-2h2"></path></svg></button></div><div role="region" tabindex="0" class="text-[0.8125rem] py-3.5 overflow-auto max-h-[600px] fd-scroll-container focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-inset focus-visible:ring-fd-ring" style="--padding-right:calc(var(--spacing) * 8)"><pre class="min-w-full w-max *:flex *:flex-col"><code><span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D"># Install the Zen models catalog</span></span>
|
|
<span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0">npm</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF"> install</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF"> @zenlm/models</span></span>
|
|
<span class="line"></span>
|
|
<span class="line"><span style="--shiki-light:#6A737D;--shiki-dark:#6A737D"># Use via the Hanzo API</span></span>
|
|
<span class="line"><span style="--shiki-light:#6F42C1;--shiki-dark:#B392F0">curl</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF"> https://api.hanzo.ai/v1/chat/completions</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF"> \</span></span>
|
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF"> -H</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF"> "Authorization: Bearer </span><span style="--shiki-light:#24292E;--shiki-dark:#E1E4E8">$HANZO_API_KEY</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF">"</span><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF"> \</span></span>
|
|
<span class="line"><span style="--shiki-light:#005CC5;--shiki-dark:#79B8FF"> -d</span><span style="--shiki-light:#032F62;--shiki-dark:#9ECBFF"> '{"model": "zen5", "messages": [{"role": "user", "content": "Hello!"}]}'</span></span></code></pre></div></figure>
|
|
<p>Or try it instantly at <a href="https://hanzo.chat?model=zen5" rel="noreferrer noopener" target="_blank">hanzo.chat</a>.</p>
|
|
<h2 class="flex scroll-m-28 flex-row items-center gap-2" id="whats-next"><a data-card="" href="#whats-next" class="peer">What's Next</a><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100" aria-hidden="true"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"></path><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"></path></svg></h2>
|
|
<p>We're actively working on Zen 5 fine-tunes for specialized domains — medicine, law, materials science — and expanding multimodal capabilities. The next release will bring native video understanding and real-time audio processing to the Zen 5 family.</p>
|
|
<p>Stay tuned.</p></div></main><!--$--><!--/$--><script src="/_next/static/chunks/e83606e8fa9cc796.js" id="_R_" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0])</script><script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\n2:I[106,[\"/_next/static/chunks/59d0ad1b64f8544e.js\"],\"RootProvider\"]\n3:I[53113,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n4:I[73211,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n5:I[10086,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"\"]\n7:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"OutletBoundary\"]\n8:\"$Sreact.suspense\"\na:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"ViewportBoundary\"]\nc:I[89923,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"MetadataBoundary\"]\ne:I[6998,[\"/_next/static/chunks/4d80e004cf4896dd.js\",\"/_next/static/chunks/350ee4303b732916.js\"],\"default\"]\n:HL[\"/_next/static/chunks/f2332aac77592f9d.css\",\"style\"]\n"])</script><script>self.__next_f.push([1,"0:{\"P\":null,\"b\":\"i-dnJM_MIpJSOCQWNJVMq\",\"c\":[\"\",\"blog\",\"zen5-release\"],\"q\":\"\",\"i\":false,\"f\":[[[\"\",{\"children\":[\"blog\",{\"children\":[[\"slug\",\"zen5-release\",\"d\"],{\"children\":[\"__PAGE__\",{}]}]}]},\"$undefined\",\"$undefined\",true],[[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/chunks/f2332aac77592f9d.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-0\",{\"src\":\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"lang\":\"en\",\"className\":\"dark\",\"suppressHydrationWarning\":true,\"children\":[\"$\",\"body\",null,{\"className\":\"antialiased\",\"children\":[\"$\",\"$L2\",null,{\"children\":[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[\"$\",\"main\",null,{\"className\":\"flex min-h-screen flex-col items-center justify-center px-4 text-center\",\"children\":[[\"$\",\"div\",null,{\"className\":\"mb-8 opacity-20\",\"children\":[\"$\",\"svg\",null,{\"width\":\"120\",\"height\":\"120\",\"viewBox\":\"0 0 120 120\",\"fill\":\"none\",\"aria-hidden\":\"true\",\"children\":[\"$\",\"circle\",null,{\"cx\":\"60\",\"cy\":\"60\",\"r\":\"50\",\"stroke\":\"currentColor\",\"strokeWidth\":\"3\",\"strokeLinecap\":\"round\",\"strokeDasharray\":\"280 40\"}]}]}],[\"$\",\"p\",null,{\"className\":\"text-xs font-mono uppercase tracking-[0.3em] text-fd-muted-foreground mb-4\",\"children\":\"404\"}],[\"$\",\"h1\",null,{\"className\":\"text-3xl font-semibold mb-3\",\"children\":\"Page not found\"}],[\"$\",\"p\",null,{\"className\":\"text-fd-muted-foreground max-w-sm mb-10\",\"children\":\"This page doesn't exist, or it may have moved. Try the documentation or head home.\"}],[\"$\",\"div\",null,{\"className\":\"flex flex-wrap gap-3 justify-center\",\"children\":[[\"$\",\"$L5\",null,{\"href\":\"/\",\"className\":\"inline-flex items-center gap-2 rounded-lg bg-fd-primary text-fd-primary-foreground px-4 py-2 text-sm font-medium hover:opacity-90 transition\",\"children\":\"Go home\"}],[\"$\",\"$L5\",null,{\"href\":\"/docs\",\"className\":\"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition\",\"children\":\"Documentation\"}],[\"$\",\"$L5\",null,{\"href\":\"/docs/models\",\"className\":\"inline-flex items-center gap-2 rounded-lg border border-fd-border bg-fd-background px-4 py-2 text-sm font-medium hover:bg-fd-muted transition\",\"children\":\"Browse models\"}]]}],[\"$\",\"p\",null,{\"className\":\"mt-16 text-xs font-mono text-fd-muted-foreground opacity-50\",\"children\":\"zenlm.org\"}]]}],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]}]}]}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[[\"$\",\"$1\",\"c\",{\"children\":[\"$L6\",[[\"$\",\"script\",\"script-0\",{\"src\":\"/_next/static/chunks/8de849ca74fc071f.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-1\",{\"src\":\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-2\",{\"src\":\"/_next/static/chunks/f19fe44237e54646.js\",\"async\":true,\"nonce\":\"$undefined\"}],[\"$\",\"script\",\"script-3\",{\"src\":\"/_next/static/chunks/cb0a883bafeb6805.js\",\"async\":true,\"nonce\":\"$undefined\"}]],[\"$\",\"$L7\",null,{\"children\":[\"$\",\"$8\",null,{\"name\":\"Next.MetadataOutlet\",\"children\":\"$@9\"}]}]]}],{},null,false,false]},null,false,false]},null,false,false]},null,false,false],[\"$\",\"$1\",\"h\",{\"children\":[null,[\"$\",\"$La\",null,{\"children\":\"$Lb\"}],[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$Lc\",null,{\"children\":[\"$\",\"$8\",null,{\"name\":\"Next.Metadata\",\"children\":\"$Ld\"}]}]}],null]}],false]],\"m\":\"$undefined\",\"G\":[\"$e\",[]],\"S\":true}\n"])</script><script>self.__next_f.push([1,"6:[\"$\",\"main\",null,{\"className\":\"mx-auto w-full max-w-2xl px-4 py-16\",\"children\":[[\"$\",\"$L5\",null,{\"href\":\"/blog\",\"className\":\"inline-flex items-center gap-1.5 text-sm text-fd-muted-foreground hover:text-fd-foreground mb-10 transition-colors\",\"children\":\"← Back to Blog\"}],[\"$\",\"div\",null,{\"className\":\"mb-8\",\"children\":[[\"$\",\"time\",null,{\"className\":\"text-xs font-mono text-fd-muted-foreground uppercase tracking-wider\",\"children\":\"February 28, 2026\"}],[\"$\",\"h1\",null,{\"className\":\"text-3xl font-bold mt-2 mb-3\",\"children\":\"Introducing Zen 5 — Our Most Capable Model Yet\"}],[\"$\",\"p\",null,{\"className\":\"text-fd-muted-foreground text-lg mb-4\",\"children\":\"Zen 5 brings 1T+ parameter scale, 2M context windows, and state-of-the-art performance across reasoning, code, and multimodal tasks.\"}],[\"$\",\"div\",null,{\"className\":\"flex items-center gap-3 pt-4 border-t border-fd-border\",\"children\":[[\"$\",\"span\",null,{\"className\":\"text-sm text-fd-muted-foreground\",\"children\":[\"By \",\"Zen LM Team\"]}],[\"$\",\"div\",null,{\"className\":\"flex gap-1.5 ml-auto\",\"children\":[[\"$\",\"span\",\"release\",{\"className\":\"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded\",\"children\":\"release\"}],[\"$\",\"span\",\"zen5\",{\"className\":\"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded\",\"children\":\"zen5\"}],[\"$\",\"span\",\"flagship\",{\"className\":\"text-[10px] font-mono uppercase tracking-wider bg-fd-muted text-fd-muted-foreground px-1.5 py-0.5 rounded\",\"children\":\"flagship\"}]]}]]}]]}],[\"$\",\"div\",null,{\"className\":\"prose dark:prose-invert max-w-none\",\"children\":[[\"$\",\"p\",null,{\"children\":[\"We're thrilled to announce the \",[\"$\",\"strong\",null,{\"children\":\"Zen 5\"}],\" family — our most capable generation of foundation models, pushing the frontier of what open models can achieve.\"]}],\"\\n\",[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"whats-new-in-zen-5\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#whats-new-in-zen-5\",\"className\":\"peer\",\"children\":\"What's New in Zen 5\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}],\"\\n\",[\"$\",\"p\",null,{\"children\":\"Zen 5 represents a major leap forward across every dimension that matters:\"}],\"\\n\",[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"scale-and-architecture\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#scale-and-architecture\",\"className\":\"peer\",\"children\":\"Scale and Architecture\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}],\"\\n\",[\"$\",\"p\",null,{\"children\":[\"Zen 5 is built on the \",[\"$\",\"strong\",null,{\"children\":\"Zen MoDE\"}],\" (Mixture of Distilled Experts) architecture — a framework that combines the best of sparse expert routing with distillation from multiple frontier models. At 1T+ total parameters with intelligent expert activation, Zen 5 achieves flagship intelligence without the inference cost of a dense trillion-parameter model.\"]}],\"\\n\",\"$Lf\",\"\\n\",\"$L10\",\"\\n\",\"$L11\",\"\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\\n\",\"$L12\",\"\\n\",\"$L13\",\"\\n\",\"$L14\",\"\\n\",\"$L15\",\"\\n\",\"$L16\",\"\\n\",\"$L17\",\"\\n\",\"$L18\",\"\\n\",\"$L19\",\"\\n\",\"$L1a\",\"\\n\",\"$L1b\",\"\\n\",\"$L1c\",\"\\n\",\"$L1d\"]}]]}]\n"])</script><script>self.__next_f.push([1,"1e:I[48068,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"default\"]\n1f:I[51504,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"CodeBlock\"]\n20:I[51504,[\"/_next/static/chunks/59d0ad1b64f8544e.js\",\"/_next/static/chunks/8de849ca74fc071f.js\",\"/_next/static/chunks/e62b91212ee7f8ff.js\",\"/_next/static/chunks/f19fe44237e54646.js\",\"/_next/static/chunks/cb0a883bafeb6805.js\"],\"Pre\"]\nf:[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"2m-context-window\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#2m-context-window\",\"className\":\"peer\",\"children\":\"2M Context Window\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n10:[\"$\",\"p\",null,{\"children\":[\"Zen 5 supports \",[\"$\",\"strong\",null,{\"children\":\"2 million tokens\"}],\" of context — enough to process entire codebases, multi-hour transcripts, or hundreds of research papers in a single request. This unlocks agentic workflows that simply weren't possible before.\"]}]\n11:[\"$\",\"h3\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"the-zen-5-family\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#the-zen-5-family\",\"className\":\"peer\",\"children\":\"The Zen 5 Family\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n"])</script><script>self.__next_f.push([1,"12:[\"$\",\"div\",null,{\"className\":\"relative overflow-auto prose-no-margin my-6\",\"children\":[\"$\",\"table\",null,{\"children\":[[\"$\",\"thead\",null,{\"children\":[\"$\",\"tr\",null,{\"children\":[[\"$\",\"th\",null,{\"children\":\"Model\"}],[\"$\",\"th\",null,{\"children\":\"Parameters\"}],[\"$\",\"th\",null,{\"children\":\"Context\"}],[\"$\",\"th\",null,{\"children\":\"Strengths\"}]]}]}],[\"$\",\"tbody\",null,{\"children\":[[\"$\",\"tr\",null,{\"children\":[[\"$\",\"td\",null,{\"children\":\"zen5\"}],[\"$\",\"td\",null,{\"children\":\"1T+ MoE\"}],[\"$\",\"td\",null,{\"children\":\"2M\"}],[\"$\",\"td\",null,{\"children\":\"Flagship reasoning, all tasks\"}]]}],[\"$\",\"tr\",null,{\"children\":[[\"$\",\"td\",null,{\"children\":\"zen5-pro\"}],[\"$\",\"td\",null,{\"children\":\"480B MoE\"}],[\"$\",\"td\",null,{\"children\":\"512K\"}],[\"$\",\"td\",null,{\"children\":\"High capability, cost-efficient\"}]]}],[\"$\",\"tr\",null,{\"children\":[[\"$\",\"td\",null,{\"children\":\"zen5-ultra\"}],[\"$\",\"td\",null,{\"children\":\"1T+ MoE\"}],[\"$\",\"td\",null,{\"children\":\"2M\"}],[\"$\",\"td\",null,{\"children\":\"Maximum reasoning depth\"}]]}],[\"$\",\"tr\",null,{\"children\":[[\"$\",\"td\",null,{\"children\":\"zen5-mini\"}],[\"$\",\"td\",null,{\"children\":\"14B\"}],[\"$\",\"td\",null,{\"children\":\"128K\"}],[\"$\",\"td\",null,{\"children\":\"Fast, lightweight inference\"}]]}],[\"$\",\"tr\",null,{\"children\":[[\"$\",\"td\",null,{\"children\":\"zen5-max\"}],[\"$\",\"td\",null,{\"children\":\"1T+ MoE\"}],[\"$\",\"td\",null,{\"children\":\"2M\"}],[\"$\",\"td\",null,{\"children\":\"Enterprise scale\"}]]}],[\"$\",\"tr\",null,{\"children\":[[\"$\",\"td\",null,{\"children\":\"zen5-coder\"}],[\"$\",\"td\",null,{\"children\":\"1T+ MoE\"}],[\"$\",\"td\",null,{\"children\":\"2M\"}],[\"$\",\"td\",null,{\"children\":\"Code generation, software engineering\"}]]}]]}]]}]}]\n"])</script><script>self.__next_f.push([1,"13:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"benchmark-performance\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#benchmark-performance\",\"className\":\"peer\",\"children\":\"Benchmark Performance\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n14:[\"$\",\"p\",null,{\"children\":\"Zen 5 achieves state-of-the-art results on major benchmarks:\"}]\n15:[\"$\",\"ul\",null,{\"children\":[\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"MMLU\"}],\": 92.1% (5-shot)\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"HumanEval\"}],\": 96.3% (pass@1)\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"MATH\"}],\": 91.7%\"]}],\"\\n\",[\"$\",\"li\",null,{\"children\":[[\"$\",\"strong\",null,{\"children\":\"GPQA Diamond\"}],\": 75.2%\"]}],\"\\n\"]}]\n16:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"open-weights\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#open-weights\",\"className\":\"peer\",\"children\":\"Open Weights\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n17:[\"$\",\"p\",null,{\"children\":[\"True to our commitment to open AI, Zen 5 weights are available on \",[\"$\",\"$L1e\",null,{\"href\":\"https://huggingface.co/zenlm/zen5\",\"children\":\"HuggingFace\"}],\" under the Zen Open License. The model runs efficiently in 4-bit quantization on consumer hardware using our optimized inference stack.\"]}]\n18:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"getting-started\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#getting-started\",\"className\":\"peer\",\"children\":\"Getting Started\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n"])</script><script>self.__next_f.push([1,"19:[\"$\",\"$L1f\",null,{\"className\":\"shiki shiki-themes github-light github-dark\",\"style\":{\"--shiki-light\":\"#24292e\",\"--shiki-dark\":\"#e1e4e8\",\"--shiki-light-bg\":\"#fff\",\"--shiki-dark-bg\":\"#24292e\"},\"tabIndex\":\"0\",\"icon\":\"\u003csvg viewBox=\\\"0 0 24 24\\\"\u003e\u003cpath d=\\\"m 4,4 a 1,1 0 0 0 -0.7070312,0.2929687 1,1 0 0 0 0,1.4140625 L 8.5859375,11 3.2929688,16.292969 a 1,1 0 0 0 0,1.414062 1,1 0 0 0 1.4140624,0 l 5.9999998,-6 a 1.0001,1.0001 0 0 0 0,-1.414062 L 4.7070312,4.2929687 A 1,1 0 0 0 4,4 Z m 8,14 a 1,1 0 0 0 -1,1 1,1 0 0 0 1,1 h 8 a 1,1 0 0 0 1,-1 1,1 0 0 0 -1,-1 z\\\" fill=\\\"currentColor\\\" /\u003e\u003c/svg\u003e\",\"children\":[\"$\",\"$L20\",null,{\"children\":[\"$\",\"code\",null,{\"children\":[[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#6A737D\",\"--shiki-dark\":\"#6A737D\"},\"children\":\"# Install the Zen models catalog\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#6F42C1\",\"--shiki-dark\":\"#B392F0\"},\"children\":\"npm\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\" install\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\" @zenlm/models\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\"}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#6A737D\",\"--shiki-dark\":\"#6A737D\"},\"children\":\"# Use via the Hanzo API\"}]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#6F42C1\",\"--shiki-dark\":\"#B392F0\"},\"children\":\"curl\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\" https://api.hanzo.ai/v1/chat/completions\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\" \\\\\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\" -H\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\" \\\"Authorization: Bearer \"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#24292E\",\"--shiki-dark\":\"#E1E4E8\"},\"children\":\"$$HANZO_API_KEY\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\"\\\"\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\" \\\\\"}]]}],\"\\n\",[\"$\",\"span\",null,{\"className\":\"line\",\"children\":[[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#005CC5\",\"--shiki-dark\":\"#79B8FF\"},\"children\":\" -d\"}],[\"$\",\"span\",null,{\"style\":{\"--shiki-light\":\"#032F62\",\"--shiki-dark\":\"#9ECBFF\"},\"children\":\" '{\\\"model\\\": \\\"zen5\\\", \\\"messages\\\": [{\\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"Hello!\\\"}]}'\"}]]}]]}]}]}]\n"])</script><script>self.__next_f.push([1,"1a:[\"$\",\"p\",null,{\"children\":[\"Or try it instantly at \",[\"$\",\"$L1e\",null,{\"href\":\"https://hanzo.chat?model=zen5\",\"children\":\"hanzo.chat\"}],\".\"]}]\n1b:[\"$\",\"h2\",null,{\"className\":\"flex scroll-m-28 flex-row items-center gap-2\",\"id\":\"whats-next\",\"children\":[[\"$\",\"a\",null,{\"data-card\":\"\",\"href\":\"#whats-next\",\"className\":\"peer\",\"children\":\"What's Next\"}],[\"$\",\"svg\",null,{\"ref\":\"$undefined\",\"xmlns\":\"http://www.w3.org/2000/svg\",\"width\":24,\"height\":24,\"viewBox\":\"0 0 24 24\",\"fill\":\"none\",\"stroke\":\"currentColor\",\"strokeWidth\":2,\"strokeLinecap\":\"round\",\"strokeLinejoin\":\"round\",\"className\":\"lucide lucide-link size-3.5 shrink-0 text-fd-muted-foreground opacity-0 transition-opacity peer-hover:opacity-100\",\"aria-hidden\":true,\"children\":[[\"$\",\"path\",\"1cjeqo\",{\"d\":\"M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71\"}],[\"$\",\"path\",\"19qd67\",{\"d\":\"M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71\"}],\"$undefined\"]}]]}]\n1c:[\"$\",\"p\",null,{\"children\":\"We're actively working on Zen 5 fine-tunes for specialized domains — medicine, law, materials science — and expanding multimodal capabilities. The next release will bring native video understanding and real-time audio processing to the Zen 5 family.\"}]\n1d:[\"$\",\"p\",null,{\"children\":\"Stay tuned.\"}]\n"])</script><script>self.__next_f.push([1,"b:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}],[\"$\",\"meta\",\"2\",{\"name\":\"theme-color\",\"media\":\"(prefers-color-scheme: dark)\",\"content\":\"#0A0A0A\"}],[\"$\",\"meta\",\"3\",{\"name\":\"theme-color\",\"media\":\"(prefers-color-scheme: light)\",\"content\":\"#fff\"}]]\n"])</script><script>self.__next_f.push([1,"9:null\nd:[[\"$\",\"title\",\"0\",{\"children\":\"Introducing Zen 5 — Our Most Capable Model Yet — Zen LM Blog | Zen LM\"}],[\"$\",\"meta\",\"1\",{\"name\":\"description\",\"content\":\"Zen 5 brings 1T+ parameter scale, 2M context windows, and state-of-the-art performance across reasoning, code, and multimodal tasks.\"}],[\"$\",\"meta\",\"2\",{\"property\":\"og:title\",\"content\":\"Zen LM - Open Foundation Models\"}],[\"$\",\"meta\",\"3\",{\"property\":\"og:description\",\"content\":\"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks.\"}],[\"$\",\"meta\",\"4\",{\"property\":\"og:url\",\"content\":\"https://zenlm.org\"}],[\"$\",\"meta\",\"5\",{\"property\":\"og:site_name\",\"content\":\"Zen LM\"}],[\"$\",\"meta\",\"6\",{\"property\":\"og:type\",\"content\":\"website\"}],[\"$\",\"meta\",\"7\",{\"name\":\"twitter:card\",\"content\":\"summary_large_image\"}],[\"$\",\"meta\",\"8\",{\"name\":\"twitter:site\",\"content\":\"@zenlmorg\"}],[\"$\",\"meta\",\"9\",{\"name\":\"twitter:creator\",\"content\":\"@zenlmorg\"}],[\"$\",\"meta\",\"10\",{\"name\":\"twitter:title\",\"content\":\"Zen LM - Open Foundation Models\"}],[\"$\",\"meta\",\"11\",{\"name\":\"twitter:description\",\"content\":\"Zen AI model family by Hanzo AI. 14 frontier models from 4B to 1T+ parameters for code, reasoning, vision, and multimodal tasks.\"}]]\n"])</script><script>
|
|
(function(){
|
|
// After React renders the lotus emoji from RSC payload, walk the DOM
|
|
// and replace it with the enso SVG. Polls so subsequent React re-renders
|
|
// also get cleaned up.
|
|
function swap(){
|
|
// 1. Replace lotus + ' Zen LM' text inside <a> brand links
|
|
document.querySelectorAll('a').forEach(function(a){
|
|
if (a.dataset.zenLotusSwapped) return;
|
|
var t = (a.textContent || '');
|
|
if (!/.*Zen LM|Zen LM.*/.test(t)) return;
|
|
// Find the lotus text node specifically
|
|
var walker = document.createTreeWalker(a, NodeFilter.SHOW_TEXT, null);
|
|
var node;
|
|
while ((node = walker.nextNode())) {
|
|
if (node.nodeValue && node.nodeValue.indexOf('') !== -1) {
|
|
node.nodeValue = node.nodeValue.replace(/\s?/g, '');
|
|
}
|
|
}
|
|
// Inject enso SVG at start
|
|
if (!a.querySelector('svg[aria-label="Zen LM"]')) {
|
|
var ns = 'http://www.w3.org/2000/svg';
|
|
var svg = document.createElementNS(ns, 'svg');
|
|
svg.setAttribute('viewBox', '0 0 512 512');
|
|
svg.setAttribute('fill', 'none');
|
|
svg.setAttribute('width', '18');
|
|
svg.setAttribute('height', '18');
|
|
svg.setAttribute('aria-label', 'Zen LM');
|
|
svg.style.cssText = 'display:inline-block;vertical-align:-2px;margin-right:6px;flex-shrink:0';
|
|
var p = document.createElementNS(ns, 'path');
|
|
p.setAttribute('d', 'M 256 84 A 172 172 0 1 0 256 428 A 172 172 0 1 0 256 84 Z');
|
|
p.setAttribute('stroke', 'currentColor');
|
|
p.setAttribute('stroke-width', '26');
|
|
p.setAttribute('stroke-linecap', 'round');
|
|
p.setAttribute('stroke-linejoin', 'round');
|
|
svg.appendChild(p);
|
|
a.insertBefore(svg, a.firstChild);
|
|
}
|
|
a.dataset.zenLotusSwapped = '1';
|
|
});
|
|
}
|
|
function start(){ swap(); setInterval(swap, 600); }
|
|
if (document.readyState !== 'loading') start();
|
|
else document.addEventListener('DOMContentLoaded', start);
|
|
})();
|
|
</script>
|
|
|
|
<style id="zenlm-brand-anim">
|
|
@keyframes zenlm-brand-draw { to { stroke-dashoffset: 0; } }
|
|
svg.zenlm-brand-svg .zenlm-brand-path {
|
|
stroke-dasharray: 1100;
|
|
stroke-dashoffset: 1100;
|
|
animation: zenlm-brand-draw 1.4s cubic-bezier(.45,0,.2,1) 0.1s 1 forwards;
|
|
}
|
|
.zen-link-icon { display: inline-block; vertical-align: middle; flex-shrink: 0; }
|
|
</style></body></html> |