{"id":60455,"date":"2026-04-18T00:05:14","date_gmt":"2026-04-17T18:35:14","guid":{"rendered":"https:\/\/officechai.com\/?p=60455"},"modified":"2026-04-18T00:05:16","modified_gmt":"2026-04-17T18:35:16","slug":"prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance","status":"publish","type":"post","link":"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/","title":{"rendered":"PrismML Releases Ternary Bonsai That Uses Just 1.58 Bits To Store Weights, Achieves 16x Memory Reduction With Comparable Performance"},"content":{"rendered":"\n<p>Even as conventional LLMs become <a href=\"https:\/\/officechai.com\/ai\/google-gemini-3-1-pro-doubles-performance-over-gemini-3-pro-on-arc-agi-2-tops-benchmark\/\">ever more powerful<\/a>, some interesting new approaches are also producing impressive results.<\/p>\n\n\n\n<p><a href=\"https:\/\/officechai.com\/ai\/prismml-1-bit-bonsai-8b\/\">PrismML<\/a>, a startup spun out of Caltech and backed by Khosla Ventures and Google, quietly released something worth paying attention to this week: <strong>Ternary Bonsai<\/strong>, a family of language models that achieve near-frontier performance at a fraction of the memory cost. In a field where the default assumption is that <a href=\"https:\/\/officechai.com\/ai\/ckaude-opus-4-7-benchmarks\/\">bigger models mean better results<\/a>, Ternary Bonsai makes a compelling case for the opposite.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">What Makes It Different<\/h2>\n\n\n\n<p>Most production language models store each weight as a 16-bit floating-point number. Ternary Bonsai strips that down to just 1.58 bits per weight \u2014 meaning every parameter in the network can only be one of three values: <strong>-1, 0, or +1<\/strong>. That&#8217;s it. No mid-range floats, no escape hatches to higher precision for &#8220;important&#8221; layers. The entire network \u2014 embeddings, attention, MLPs, the language model head \u2014 uses this ternary representation throughout.<\/p>\n\n\n\n<p>To preserve useful signal despite such extreme compression, the model uses group-wise quantization: for every 128 weights, a shared FP16 scale factor <code>s<\/code> is stored, so each weight is effectively <code>{-s, 0, +s}<\/code>. This lets the model adapt its effective weight magnitude to different parts of the network, while keeping the per-weight storage cost nearly as low as binary.<\/p>\n\n\n\n<p>The result is a 9x reduction in memory footprint compared to standard 16-bit models.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">The Numbers<\/h2>\n\n\n\n<p>The 8B version of Ternary Bonsai fits in just <strong>1.75 GB<\/strong> \u2014 smaller than many smartphone apps \u2014 and scores <strong>75.5<\/strong> on average across six benchmarks (MMLU Redux, MuSR, GSM8K, HumanEval+, IFEval, BFCLv3). For context, that puts it ahead of RNJ 8B (73.1), Ministral3 8B (71.0), Llama 3.1 8B (67.1), and a dozen other models \u2014 all of which require 14\u201318 GB of memory.<\/p>\n\n\n\n<p>Only Qwen3 8B, at 79.3 average and 16.38 GB, beats it in the 8B class.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img data-recalc-dims=\"1\" fetchpriority=\"high\" decoding=\"async\" width=\"640\" height=\"362\" src=\"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/image-47.png?resize=640%2C362&#038;ssl=1\" alt=\"\" class=\"wp-image-60456\" srcset=\"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/image-47.png?w=952&amp;ssl=1 952w, https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/image-47.png?resize=300%2C170&amp;ssl=1 300w, https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/image-47.png?resize=768%2C434&amp;ssl=1 768w\" sizes=\"(max-width: 640px) 100vw, 640px\" \/><\/figure>\n\n\n\n<p>The intelligence density chart tells the starkest story. While most 8B models cluster between 0.05 and 0.10 per GB, Ternary Bonsai 8B scores <strong>0.803<\/strong> \u2014 roughly 10x better than Qwen3 8B, and second only to the even-more-compressed 1-bit Bonsai 8B at 1.060.<\/p>\n\n\n\n<figure class=\"wp-block-image size-full\"><img data-recalc-dims=\"1\" decoding=\"async\" width=\"640\" height=\"323\" data-src=\"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/image-49.png?resize=640%2C323&#038;ssl=1\" alt=\"\" class=\"wp-image-60458 lazyload\" data-srcset=\"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/image-49.png?w=990&amp;ssl=1 990w, https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/image-49.png?resize=300%2C152&amp;ssl=1 300w, https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/image-49.png?resize=768%2C388&amp;ssl=1 768w\" data-sizes=\"(max-width: 640px) 100vw, 640px\" src=\"data:image\/svg+xml;base64,PHN2ZyB3aWR0aD0iMSIgaGVpZ2h0PSIxIiB4bWxucz0iaHR0cDovL3d3dy53My5vcmcvMjAwMC9zdmciPjwvc3ZnPg==\" style=\"--smush-placeholder-width: 640px; --smush-placeholder-aspect-ratio: 640\/323;\" \/><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">On-Device Performance<\/h2>\n\n\n\n<p>The implications for edge AI deployment are significant. On an M4 Pro Mac, Ternary Bonsai 8B runs at <strong>82 tokens per second<\/strong> \u2014 around 5x faster than a standard 16-bit 8B model. On an iPhone 17 Pro Max, it hits <strong>27 tokens\/sec<\/strong>, with energy consumption of just 0.132 mWh per token. That&#8217;s 3\u20134x more energy efficient than full-precision alternatives.<\/p>\n\n\n\n<p>These are the kinds of numbers that make on-device AI \u2014 without a cloud call, without latency, without data leaving the device \u2014 genuinely practical. The models run natively on Apple hardware via MLX and are available today under the Apache 2.0 License.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">A New Point on the Curve<\/h2>\n\n\n\n<p>Ternary Bonsai is not a replacement for the company&#8217;s earlier 1-bit Bonsai family. Where absolute minimum footprint matters most, 1-bit still wins. But Ternary Bonsai offers a different tradeoff: a 600 MB increase in size buys a 5-point jump in average benchmark score. Across the 1.7B, 4B, and 8B variants, that tradeoff scales predictably, giving developers a real menu of options rather than a binary choice.<\/p>\n\n\n\n<p>At a time when <a href=\"https:\/\/officechai.com\/ai\/geminis-traffic-share-rises-above-25-in-march-2026-chatgpt-slips-to-56-similarweb-data\/\">AI model competition<\/a> is largely defined by who can spend more on compute and data, PrismML is making a different bet: that extreme compression, done right, can be its own competitive advantage. The early results suggest they might be onto something.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Even as conventional LLMs become ever more powerful, some interesting new approaches are also producing impressive results. PrismML, a startup spun out of&#8230;<\/p>\n","protected":false},"author":1,"featured_media":60459,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[1029],"tags":[],"class_list":["post-60455","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.5 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>PrismML Releases Ternary Bonsai That Uses Just 1.58 Bits To Store Weights, Achieves 16x Memory Reduction With Comparable Performance<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"PrismML Releases Ternary Bonsai That Uses Just 1.58 Bits To Store Weights, Achieves 16x Memory Reduction With Comparable Performance\" \/>\n<meta property=\"og:description\" content=\"Even as conventional LLMs become ever more powerful, some interesting new approaches are also producing impressive results. PrismML, a startup spun out of...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/\" \/>\n<meta property=\"og:site_name\" content=\"OfficeChai\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/OfficeChai\/\" \/>\n<meta property=\"article:published_time\" content=\"2026-04-17T18:35:14+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2026-04-17T18:35:16+00:00\" \/>\n<meta property=\"og:image\" content=\"http:\/\/officechai.com\/wp-content\/uploads\/2026\/04\/WhatsApp-Image-2026-04-18-at-00.02.58.jpeg\" \/>\n\t<meta property=\"og:image:width\" content=\"1541\" \/>\n\t<meta property=\"og:image:height\" content=\"758\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/jpeg\" \/>\n<meta name=\"author\" content=\"OfficeChai Team\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@OfficeChai\" \/>\n<meta name=\"twitter:site\" content=\"@OfficeChai\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"OfficeChai Team\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/\",\"url\":\"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/\",\"name\":\"PrismML Releases Ternary Bonsai That Uses Just 1.58 Bits To Store Weights, Achieves 16x Memory Reduction With Comparable Performance\",\"isPartOf\":{\"@id\":\"https:\/\/officechai.com\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/WhatsApp-Image-2026-04-18-at-00.02.58.jpeg?fit=1541%2C758&ssl=1\",\"datePublished\":\"2026-04-17T18:35:14+00:00\",\"dateModified\":\"2026-04-17T18:35:16+00:00\",\"author\":{\"@id\":\"https:\/\/officechai.com\/#\/schema\/person\/5861f1134993293cc28905de7624d6b2\"},\"breadcrumb\":{\"@id\":\"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/#primaryimage\",\"url\":\"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/WhatsApp-Image-2026-04-18-at-00.02.58.jpeg?fit=1541%2C758&ssl=1\",\"contentUrl\":\"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/WhatsApp-Image-2026-04-18-at-00.02.58.jpeg?fit=1541%2C758&ssl=1\",\"width\":1541,\"height\":758,\"caption\":\"prismml\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/officechai.com\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"PrismML Releases Ternary Bonsai That Uses Just 1.58 Bits To Store Weights, Achieves 16x Memory Reduction With Comparable Performance\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/officechai.com\/#website\",\"url\":\"https:\/\/officechai.com\/\",\"name\":\"OfficeChai\",\"description\":\"Startups, Businesses And Careers\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/officechai.com\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/officechai.com\/#\/schema\/person\/5861f1134993293cc28905de7624d6b2\",\"name\":\"OfficeChai Team\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/officechai.com\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/61d744733248dc647d505d0676bb425323413132ee5447e86aa8eecbbb7b27d5?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/61d744733248dc647d505d0676bb425323413132ee5447e86aa8eecbbb7b27d5?s=96&d=mm&r=g\",\"caption\":\"OfficeChai Team\"},\"description\":\"Dotting the i's, crossing the t's.\",\"url\":\"https:\/\/officechai.com\/author\/admin\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"PrismML Releases Ternary Bonsai That Uses Just 1.58 Bits To Store Weights, Achieves 16x Memory Reduction With Comparable Performance","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/","og_locale":"en_US","og_type":"article","og_title":"PrismML Releases Ternary Bonsai That Uses Just 1.58 Bits To Store Weights, Achieves 16x Memory Reduction With Comparable Performance","og_description":"Even as conventional LLMs become ever more powerful, some interesting new approaches are also producing impressive results. PrismML, a startup spun out of...","og_url":"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/","og_site_name":"OfficeChai","article_publisher":"https:\/\/www.facebook.com\/OfficeChai\/","article_published_time":"2026-04-17T18:35:14+00:00","article_modified_time":"2026-04-17T18:35:16+00:00","og_image":[{"width":1541,"height":758,"url":"http:\/\/officechai.com\/wp-content\/uploads\/2026\/04\/WhatsApp-Image-2026-04-18-at-00.02.58.jpeg","type":"image\/jpeg"}],"author":"OfficeChai Team","twitter_card":"summary_large_image","twitter_creator":"@OfficeChai","twitter_site":"@OfficeChai","twitter_misc":{"Written by":"OfficeChai Team","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/","url":"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/","name":"PrismML Releases Ternary Bonsai That Uses Just 1.58 Bits To Store Weights, Achieves 16x Memory Reduction With Comparable Performance","isPartOf":{"@id":"https:\/\/officechai.com\/#website"},"primaryImageOfPage":{"@id":"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/#primaryimage"},"image":{"@id":"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/#primaryimage"},"thumbnailUrl":"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/WhatsApp-Image-2026-04-18-at-00.02.58.jpeg?fit=1541%2C758&ssl=1","datePublished":"2026-04-17T18:35:14+00:00","dateModified":"2026-04-17T18:35:16+00:00","author":{"@id":"https:\/\/officechai.com\/#\/schema\/person\/5861f1134993293cc28905de7624d6b2"},"breadcrumb":{"@id":"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/#primaryimage","url":"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/WhatsApp-Image-2026-04-18-at-00.02.58.jpeg?fit=1541%2C758&ssl=1","contentUrl":"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/WhatsApp-Image-2026-04-18-at-00.02.58.jpeg?fit=1541%2C758&ssl=1","width":1541,"height":758,"caption":"prismml"},{"@type":"BreadcrumbList","@id":"https:\/\/officechai.com\/ai\/prismml-releases-ternary-bonsai-that-uses-just-1-58-bits-to-store-weights-achieves-16x-memory-reduction-with-comparable-performance\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/officechai.com\/"},{"@type":"ListItem","position":2,"name":"PrismML Releases Ternary Bonsai That Uses Just 1.58 Bits To Store Weights, Achieves 16x Memory Reduction With Comparable Performance"}]},{"@type":"WebSite","@id":"https:\/\/officechai.com\/#website","url":"https:\/\/officechai.com\/","name":"OfficeChai","description":"Startups, Businesses And Careers","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/officechai.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/officechai.com\/#\/schema\/person\/5861f1134993293cc28905de7624d6b2","name":"OfficeChai Team","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/officechai.com\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/61d744733248dc647d505d0676bb425323413132ee5447e86aa8eecbbb7b27d5?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/61d744733248dc647d505d0676bb425323413132ee5447e86aa8eecbbb7b27d5?s=96&d=mm&r=g","caption":"OfficeChai Team"},"description":"Dotting the i's, crossing the t's.","url":"https:\/\/officechai.com\/author\/admin\/"}]}},"jetpack_featured_media_url":"https:\/\/i0.wp.com\/officechai.com\/wp-content\/uploads\/2026\/04\/WhatsApp-Image-2026-04-18-at-00.02.58.jpeg?fit=1541%2C758&ssl=1","jetpack_shortlink":"https:\/\/wp.me\/p685C6-fJ5","jetpack_likes_enabled":true,"jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/posts\/60455","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/comments?post=60455"}],"version-history":[{"count":1,"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/posts\/60455\/revisions"}],"predecessor-version":[{"id":60460,"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/posts\/60455\/revisions\/60460"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/media\/60459"}],"wp:attachment":[{"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/media?parent=60455"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/categories?post=60455"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/officechai.com\/wp-json\/wp\/v2\/tags?post=60455"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}