{"id":595,"date":"2026-10-23T07:06:31","date_gmt":"2026-10-22T23:06:31","guid":{"rendered":"https:\/\/aidashxp.com\/openai-decisions-api-launch\/"},"modified":"2026-10-23T07:06:47","modified_gmt":"2026-10-22T23:06:47","slug":"openai-decisions-api-launch","status":"publish","type":"post","link":"https:\/\/aidashxp.com\/en\/openai-decisions-api-launch\/","title":{"rendered":"OpenAI Decisions API fully launched: The decision-model race begins, with latency reduced to 100 ms"},"content":{"rendered":"<p class=\"wp-block-paragraph\">OpenAI fully opened <strong>Decisions API<\/strong> to all customers on October 22 (Thursday). This product debuted at Developer Day on September 29 and now supports both speech and vision modalities, with inference resources reallocated globally to minimize latency<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">It sounds like just another routine API launch\u2014but the category it occupies deserves separate attention<strong>decision models<\/strong>\u2014 Not generating text, not performing reasoning chains; instead, rapidly presenting a set of options and selecting one, along with confidence scores. Over the past year, this category evolved from TypeSafe\u2019s sole concept into a competitive arena where OpenAI, Microsoft, Amazon, and Liquid AI are all actively competing<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">OpenAI\u2019s approach: No new model training\u2014just speed up Luna<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">Most notably, OpenAI\u2019s implementation path: They did not train a new \u201ccalibrated decision model,\u201d but instead repurposed <strong><a href=\"https:\/\/chatgpt.com\" target=\"_blank\" rel=\"nofollow noopener\">ChatGPT<\/a> Luna<\/strong> Repurpose and reconfigure to accelerate inference speed and reduce per-call cost. Nikunj Handa, OpenAI API Product Lead, told TechCrunch plainly: \u201cWe may train specialized models for these capabilities in the future. But right now, it\u2019s the legacy Luna doing the work.\u201d<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">The primary impact is on latency. Handa cited figures dropping from the original 1\u20133 seconds to <strong>100, 120, and 180 milliseconds<\/strong>Among early adopters, Speak\u2019s CTO reported wait time between actions fell from 1.4 seconds to 0.13 seconds. Box, Datadog, and Ramp are also replacing their existing LLM calls with this API to achieve higher throughput.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">This approach aligns with the earlier-discussed \u201crouting wizard\u201d logic: many business scenarios don\u2019t require a large language model to generate eloquent text\u2014only to decide \u201cwhat to do next\u201d within hundreds of milliseconds. Using flagship models for such tasks is like delivering parcels by truck. <a href=\"https:\/\/aidashxp.com\/en\/microsoft-decision-1-review\/\">Microsoft-Decision-1<\/a> Real-world rankings: OpenAI is not number one<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">According to third-party benchmarks, OpenAI entered this market late\u2014and its first iteration holds no advantage:<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">On two independent evaluation indices,<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>TypeSafe\u2019s latest Jev model<strong>ranks 7th and 3rd, while OpenAI\u2019s Decision Model ranks<\/strong>8th and 14th<strong>Evaluators favor Liquid\u2019s model, released last week, and Base Lab\u2019s model more highly.<\/strong><\/li>\n<li>On the \u201cPac-Man decision-making\u201d benchmark, Jev\u2019s latest version ranks first. <strong>D1 Ultra<\/strong> OpenAI\u2019s differentiation lies in <strong>Elephant-1<\/strong><\/li>\n<li>multimodality. Handa stated Luna is \u201cexceptionally strong at image classification, with superior calibration,\u201d and customers want the API to support images as part of its output. In other words, OpenAI isn\u2019t competing head-on for pure speed rankings; instead, it leverages versatility\u2014\u201cseeing images, hearing audio, and generating visual outputs\u201d\u2014to cover workloads that single-point decision models cannot handle\u2014a strategy distinct from<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">Jev\u2019s singular-excellence approach<strong>multimodal<\/strong>\u3002Handa \u8bf4\u5728\u56fe\u50cf\u5206\u7c7b\u4efb\u52a1\u4e0a&#8221;Luna \u6781\u5f3a\uff0c\u6821\u51c6\u8868\u73b0\u66f4\u597d&#8221;\uff0c\u5ba2\u6237\u4e5f\u5e0c\u671b API \u80fd\u652f\u6301\u4ee5\u56fe\u50cf\u4f5c\u4e3a\u8f93\u51fa\u7684\u4e00\u90e8\u5206\u3002\u4e5f\u5c31\u662f\u8bf4\uff0cOpenAI \u4e0d\u6253\u7b97\u5728\u7eaf\u901f\u5ea6\u699c\u4e0a\u786c\u62fc\uff0c\u800c\u662f\u7528&#8221;\u80fd\u770b\u56fe\u3001\u80fd\u542c\u58f0\u97f3\u3001\u8fd8\u80fd\u8f93\u51fa\u89c6\u89c9\u7ed3\u679c&#8221;\u7684\u901a\u7528\u6027\u53bb\u8986\u76d6\u90a3\u4e9b\u5355\u4e00\u51b3\u7b56\u6a21\u578b\u6253\u4e0d\u4e86\u7684\u5de5\u4f5c\u8d1f\u8f7d\u2014\u2014\u8fd9\u4e00\u70b9\u548c <a href=\"https:\/\/aidashxp.com\/en\/jev-typesafe-review\/\">Jev \u7684\u5355\u70b9\u6781\u81f4\u8def\u7ebf<\/a>\u5f62\u6210\u660e\u663e\u5bf9\u7167\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">What this means for developers<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u51e0\u4e2a\u73b0\u5b9e\u5f71\u54cd\uff1a<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>\u6210\u672c\u7ed3\u6784\u53d8\u4e86<\/strong>\uff1a\u628a\u6bcf\u79d2\u90fd\u5728\u8dd1\u7684\u9ad8\u9891\u5224\u65ad\uff08\u8def\u7531\u3001\u5206\u7c7b\u3001\u8fc7\u6ee4\u3001\u4e0b\u4e00\u6b65\u52a8\u4f5c\uff09\u4ece\u65d7\u8230\u6a21\u578b\u8fc1\u5230\u51b3\u7b56 API\uff0c\u8d26\u5355\u5143\u4ef6\u4ece&#8221;\u6bcf\u5343 token&#8221;\u53d8\u6210&#8221;\u6bcf\u5343\u6b21\u5224\u65ad&#8221;\uff0c\u91cf\u7ea7\u5dee\u51e0\u5341\u500d<\/li>\n<li><strong>\u4ea4\u4e92\u8bbe\u8ba1\u89e3\u9501<\/strong>\uff1a100 \u6beb\u79d2\u7ea7\u5224\u65ad\u610f\u5473\u7740\u53ef\u4ee5\u653e\u8fdb\u5b9e\u65f6\u8bed\u97f3\u5bf9\u8bdd\u3001\u6e38\u620f\u5e27\u5faa\u73af\u3001Agent \u7684\u6bcf\u4e2a\u52a8\u4f5c\u8282\u70b9\u3002Handa \u5df2\u7ecf\u5728\u8c08 60 \u6beb\u79d2\u3001\u6bcf\u5e27\u4e00\u6b21\u7684\u8bbe\u60f3<\/li>\n<li><strong>\u9009\u578b\u6ca1\u6709\u6807\u51c6\u7b54\u6848<\/strong>\uff1aTypeSafe CEO Diogo Almeida \u516c\u5f00\u8868\u793a\u4e0d\u4fe1\u4efb benchmark\uff0c\u5efa\u8bae\u5404\u5bb6\u5728\u81ea\u5df1\u7684\u5de5\u4f5c\u8d1f\u8f7d\u4e0a\u5b9e\u6d4b\u3002\u6821\u51c6\u5ea6\u3001\u6210\u672c\u3001\u901f\u5ea6\u4e09\u8005\u7684\u6700\u4f18\u70b9\u56e0\u573a\u666f\u800c\u5f02<\/li>\n<li><strong>\u591a\u6a21\u6001\u662f\u771f\u95e8\u69db<\/strong>\uff1a\u5982\u679c\u4f60\u7684\u5224\u65ad\u94fe\u8def\u91cc\u9700\u8981\u8bfb\u56fe\uff08\u622a\u56fe\u5206\u7c7b\u3001UI \u5143\u7d20\u8bc6\u522b\u3001\u89c6\u89c9\u8d28\u68c0\uff09\uff0cOpenAI \u8fd9\u6761\u8def\u76ee\u524d\u66f4\u7701\u4e8b<\/li>\n<\/ul>\n\n\n\n<h2 class=\"wp-block-heading\">\u8fd9\u4e2a\u8d5b\u9053\u7684\u672c\u8d28\uff1a\u628a&#8221;\u667a\u80fd&#8221;\u505a\u6210\u6c34\u7535<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">TypeSafe \u7ed9\u6a21\u578b\u53d6\u540d Jev\uff0c\u6765\u81ea\u7ecf\u6d4e\u5b66\u5bb6 Jevons\u2014\u2014\u4ed6\u63d0\u51fa\u63d0\u9ad8\u8d44\u6e90\u4f7f\u7528\u6548\u7387\u53cd\u800c\u4f1a\u589e\u52a0\u603b\u6d88\u8017\uff08\u6770\u6587\u65af\u6096\u8bba\uff09\u3002\u8fd9\u4e2a\u6bd4\u55bb\u653e\u5728\u51b3\u7b56\u6a21\u578b\u4e0a\u5f88\u8d34\u5207\uff1a\u5f53\u4e00\u6b21\u5224\u65ad\u4fbf\u5b9c\u5230\u53ef\u4ee5\u5ffd\u7565\u4e0d\u8ba1\uff0c\u4ea7\u54c1\u5c31\u4f1a\u5f00\u59cb\u75af\u72c2\u5730\u5224\u65ad\u2014\u2014\u6bcf\u4e00\u4e2a\u52a8\u4f5c\u3001\u6bcf\u4e00\u5e27\u3001\u6bcf\u4e00\u6b21\u70b9\u51fb\u90fd\u8fc7\u4e00\u6b21\u6a21\u578b\u3002\u9700\u6c42\u4e0d\u662f\u88ab\u6ee1\u8db3\uff0c\u662f\u88ab\u521b\u9020\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u4ece\u8fd9\u4e2a\u89d2\u5ea6\u770b\uff0cOpenAI \u628a <a href=\"https:\/\/aidashxp.com\/en\/gpt-6-1-sol-review\/\">GPT-6.1 Luna<\/a> \u6539\u4e00\u6539\u5c31\u4e0a\u7ebf\uff0c\u6070\u6070\u8bf4\u660e\u5b83\u5224\u65ad\u8fd9\u6ce2\u673a\u4f1a\u5728&#8221;\u94fa\u91cf&#8221;\u800c\u4e0d\u5728&#8221;\u7cbe\u5ea6&#8221;\uff1a\u5148\u7528\u5df2\u6709\u6a21\u578b\u628a\u5f00\u53d1\u8005\u7684\u9ad8\u9891\u8c03\u7528\u4e60\u60ef\u5360\u4f4f\uff0c\u518d\u9760\u540e\u7eed\u4e13\u95e8\u8bad\u7ec3\u628a\u8d28\u91cf\u8865\u4e0a\u3002\u76ee\u524d\u8fd9\u4e2a\u8d5b\u9053\u7684\u73a9\u5bb6\u9664\u4e86 TypeSafe \u548c OpenAI\uff0c\u8fd8\u6709\u5f00\u6e90\u53ef\u672c\u5730\u8dd1\u7684 <a href=\"https:\/\/aidashxp.com\/en\/amazon-strands-decider-2b-decision-model\/\">Amazon Strands Decider 2B<\/a>\uff0c\u4ee5\u53ca\u521a\u62ff\u5230 75 \u4ebf\u7f8e\u5143\u4f30\u503c\u7684 <a href=\"https:\/\/aidashxp.com\/en\/jev-typesafe-75b-decision-model\/\">TypeSafe \u8d44\u672c\u6545\u4e8b<\/a>\u2014\u2014\u4e09\u6761\u8def\u7ebf\uff08\u95ed\u6e90 API\u3001\u5f00\u6e90\u672c\u5730\u3001\u4e13\u7cbe\u6307\u6807\uff09\u5df2\u7ecf\u5f00\u59cb\u5206\u91ce\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Frequently Asked Questions (FAQ)<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\">OpenAI Decisions API \u662f\u4ec0\u4e48\uff1f<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e00\u4e2a\u9762\u5411&#8221;\u5feb\u901f\u5224\u65ad&#8221;\u573a\u666f\u7684 API\uff1a\u7ed9\u6a21\u578b\u4e00\u7ec4\u9009\u9879\uff0c\u5b83\u5728 100\uff5e180 \u6beb\u79d2\u5185\u9009\u51fa\u7ed3\u679c\u5e76\u7ed9\u51fa\u7f6e\u4fe1\u5ea6\uff0c\u66ff\u4ee3\u5927\u6a21\u578b\u53bb\u505a\u8def\u7531\u3001\u5206\u7c7b\u3001\u4e0b\u4e00\u6b65\u52a8\u4f5c\u8fd9\u7c7b\u9ad8\u9891\u5c0f\u51b3\u7b56\u3002\u5b83\u57fa\u4e8e <a href=\"https:\/\/chatgpt.com\" target=\"_blank\" rel=\"nofollow noopener\">ChatGPT<\/a> Luna \u91cd\u65b0\u914d\u7f6e\uff0c\u4e0d\u662f\u4e13\u95e8\u8bad\u7ec3\u7684\u65b0\u6a21\u578b\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u51b3\u7b56\u6a21\u578b\u548c\u666e\u901a\u5927\u6a21\u578b\u6709\u4ec0\u4e48\u533a\u522b\uff1f<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u666e\u901a\u5927\u6a21\u578b\u64c5\u957f\u751f\u6210\u6587\u672c\u548c\u505a\u591a\u6b65\u63a8\u7406\uff0c\u4f46\u6162\u4e14\u8d35\uff1b\u51b3\u7b56\u6a21\u578b\u53ea\u505a&#8221;\u9009\u54ea\u4e2a&#8221;\u548c&#8221;\u6709\u591a\u786e\u5b9a&#8221;\uff0c\u901f\u5ea6\u5728\u767e\u6beb\u79d2\u7ea7\uff0c\u6210\u672c\u4f4e\u4e00\u4e2a\u91cf\u7ea7\u3002\u9002\u5408\u653e\u8fdb\u5b9e\u65f6\u4ea4\u4e92\u94fe\u8def\uff0c\u4e0d\u9002\u5408\u5199\u6587\u6848\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">OpenAI \u7684\u51b3\u7b56\u6a21\u578b\u6392\u540d\u7b2c\u4e00\u5417\uff1f<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u4e0d\u662f\u3002\u5728\u7b2c\u4e09\u65b9\u51b3\u7b56\u6a21\u578b\u6307\u6570\u4e0a\uff0cTypeSafe \u7684 Jev \u6392\u5728\u7b2c 3 \u548c\u7b2c 7\uff0cOpenAI \u7684 Decision Model \u6392\u7b2c 8 \u548c\u7b2c 14\u3002OpenAI \u7684\u4f18\u52bf\u5728\u591a\u6a21\u6001\uff08\u80fd\u8bfb\u56fe\u3001\u652f\u6301\u89c6\u89c9\u8f93\u51fa\uff09\u548c\u751f\u6001\u6574\u5408\uff0c\u4e0d\u5728\u5355\u9879\u6307\u6807\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u666e\u901a\u5f00\u53d1\u8005\u600e\u4e48\u7528\u4e0a\uff1f<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Decisions API \u5df2\u5bf9\u6240\u6709 OpenAI API \u5ba2\u6237\u5f00\u653e\uff0c10 \u6708\u8d77\u8865\u9f50\u4e86\u8bed\u97f3\u548c\u89c6\u89c9\u6a21\u6001\u3002\u6309\u8c03\u7528\u91cf\u8ba1\u8d39\uff0c\u9002\u5408\u5148\u5728\u8def\u7531\u3001\u610f\u56fe\u5206\u7c7b\u8fd9\u7c7b\u4f4e\u98ce\u9669\u73af\u8282\u505a\u5bf9\u6bd4\u6d4b\u8bd5\uff0c\u518d\u51b3\u5b9a\u662f\u5426\u66ff\u6362\u73b0\u6709 LLM \u8c03\u7528\u3002<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">Summarize<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u51b3\u7b56\u6a21\u578b\u8fd9\u6761\u7ebf\u5728\u534a\u5e74\u5185\u8d70\u5b8c\u4e86&#8221;\u8bba\u6587\u6982\u5ff5 \u2192 \u521b\u4e1a\u516c\u53f8 \u2192 \u5de8\u5934\u8ddf\u8fdb \u2192 \u4ef7\u683c\u6218&#8221;\u7684\u5168\u6d41\u7a0b\u3002OpenAI \u8fd9\u4e00\u624b\u4e0d\u60ca\u8273\u4f46\u5f88\u6709\u6548\uff1a\u7528\u73b0\u6210\u6a21\u578b + \u57fa\u7840\u8bbe\u65bd\u4f18\u5316\uff0c\u5148\u628a\u5ef6\u8fdf\u6253\u8fdb\u767e\u6beb\u79d2\u533a\u95f4\uff0c\u628a\u573a\u666f\u94fa\u5f00\u3002\u771f\u6b63\u503c\u5f97\u76ef\u7684\u662f\u63a5\u4e0b\u6765\u4e13\u95e8\u8bad\u7ec3\u7684\u7248\u672c\u2014\u2014\u4ee5\u53ca\u5f53\u5224\u65ad\u6210\u672c\u8d8b\u8fd1\u4e8e\u96f6\u65f6\uff0c\u4ea7\u54c1\u5f62\u6001\u4f1a\u53d8\u6210\u4ec0\u4e48\u6837\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u60f3\u7ee7\u7eed\u6df1\u6316 AI \u6a21\u578b\u9009\u578b\uff1f\u67e5\u770b <a href=\"https:\/\/aidashxp.com\/en\/ai-models\/\">AI Model Library<\/a> and <a href=\"https:\/\/aidashxp.com\/en\/compare-tools\/\">Tool Comparison Engine<\/a>\uff0c\u6216\u9605\u8bfb\uff1a<a href=\"https:\/\/aidashxp.com\/en\/openai-devday-2026-recap\/\">OpenAI DevDay 2026 \u5168\u76d8\u70b9<\/a> \u00b7 <a href=\"https:\/\/aidashxp.com\/en\/liquid-ai-lfm-2-5-24b-a2b\/\">Liquid AI LFM 2.5 \u53d1\u5e03<\/a> \u00b7 <a href=\"https:\/\/aidashxp.com\/en\/replit-drops-anthropic-ai-coding\/\">Replit deprecates Anthropic<\/a>.<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/aidashxp.com\/en\/\">AI Dash<\/a> \u2014 Discover the best AI tools<\/p>","protected":false},"excerpt":{"rendered":"<p>OpenAI \u5728 10 \u6708 22 \u65e5\uff08\u5468 [&hellip;]<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[46],"tags":[],"class_list":["post-595","post","type-post","status-publish","format-standard","hentry","category-ai-news"],"_links":{"self":[{"href":"https:\/\/aidashxp.com\/en\/wp-json\/wp\/v2\/posts\/595","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aidashxp.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aidashxp.com\/en\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/aidashxp.com\/en\/wp-json\/wp\/v2\/comments?post=595"}],"version-history":[{"count":1,"href":"https:\/\/aidashxp.com\/en\/wp-json\/wp\/v2\/posts\/595\/revisions"}],"predecessor-version":[{"id":596,"href":"https:\/\/aidashxp.com\/en\/wp-json\/wp\/v2\/posts\/595\/revisions\/596"}],"wp:attachment":[{"href":"https:\/\/aidashxp.com\/en\/wp-json\/wp\/v2\/media?parent=595"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aidashxp.com\/en\/wp-json\/wp\/v2\/categories?post=595"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aidashxp.com\/en\/wp-json\/wp\/v2\/tags?post=595"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}