{"id":683524,"date":"2025-08-06T07:20:20","date_gmt":"2025-08-06T04:20:20","guid":{"rendered":"https:\/\/buradabiliyorum.com\/en\/openai-launches-two-open-ai-reasoning-models\/"},"modified":"2025-08-06T07:20:20","modified_gmt":"2025-08-06T04:20:20","slug":"openai-launches-two-open-ai-reasoning-models","status":"publish","type":"post","link":"https:\/\/buradabiliyorum.com\/en\/openai-launches-two-open-ai-reasoning-models\/","title":{"rendered":"OpenAI launches two &#8216;open&#8217; AI reasoning models"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_84 counter-hierarchy ez-toc-counter ez-toc-custom ez-toc-container-direction\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<label for=\"ez-toc-cssicon-toggle-item-6a26bbd89b2b7\" class=\"ez-toc-cssicon-toggle-label\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #dd3333;color:#dd3333\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #dd3333;color:#dd3333\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/label><input type=\"checkbox\"  id=\"ez-toc-cssicon-toggle-item-6a26bbd89b2b7\" checked aria-label=\"Toggle\" \/><nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/buradabiliyorum.com\/en\/openai-launches-two-open-ai-reasoning-models\/#How_the_models_performed\" >How the models performed<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-2'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/buradabiliyorum.com\/en\/openai-launches-two-open-ai-reasoning-models\/#Training_the_new_models\" >Training the new models<\/a><\/li><\/ul><\/nav><\/div>\n<div>\n<p id=\"speakable-summary\" class=\"wp-block-paragraph\">OpenAI announced Tuesday the launch of two open-weight AI reasoning models with similar capabilities to its o-<a href=\"https:\/\/buradabiliyorum.com\/en\/category\/watch-movies-tv-seriess\/\" data-internallinksmanager029f6b8e52c=\"8\" title=\"Watch Movies &amp; TV Series\" target=\"_blank\" rel=\"noopener\">series<\/a>. Both are freely available to <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/download-scripts-themes-apps\/\" data-internallinksmanager029f6b8e52c=\"9\" title=\"Download Scripts &amp; Themes &amp; Apps\" target=\"_blank\" rel=\"noopener\">download<\/a> from the online developer platform <a rel=\"nofollow\" target=\"_blank\" href=\"https:\/\/huggingface.co\/\" target=\"_blank\" rel=\"noreferrer noopener nofollow\">Hugging Face<\/a>, the company said, describing the models as \u201cstate of the art\u201d when measured across several benchmarks for comparing open models.<\/p>\n<p class=\"wp-block-paragraph\">The models come in two sizes: a larger and more capable gpt-oss-120b model that can run on a single Nvidia GPU, and a lighter-weight gpt-oss-20b model that can run on a consumer laptop with 16GB of memory.<\/p>\n<p class=\"wp-block-paragraph\">The launch marks OpenAI\u2019s first \u2018open\u2019 language model since GPT-2, which was released more than five years ago. <\/p>\n<p class=\"wp-block-paragraph\">In a briefing, OpenAI said its open models will be capable of sending complex queries to AI models in the cloud, as TechCrunch previously reported. That means if OpenAI\u2019s open model is not capable of a certain task, such as processing an image, developers can connect the open model to one of the company\u2019s more capable closed models.<\/p>\n<p class=\"wp-block-paragraph\">While OpenAI open sourced AI models in its early days, the company has <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/general\/\" data-internallinksmanager029f6b8e52c=\"3\" title=\"General\" target=\"_blank\" rel=\"noopener\">general<\/a>ly favored a proprietary, closed source development approach. The latter strategy has helped OpenAI build a large business selling access to its AI models via an API to enterprises and developers.<\/p>\n<p class=\"wp-block-paragraph\">However, CEO Sam Altman said in January he believes OpenAI has been \u201con the wrong side of history\u201d when it comes to open sourcing its technologies. The company today faces growing pressure from Chinese AI labs \u2014 including DeepSeek, Alibaba\u2019s Qwen, and Moonshot AI \u2014 which have developed several of the world\u2019s most capable and popular open models. (While Meta previously dominated the open AI space, the company\u2019s Llama AI models have fallen behind in the last year.)<\/p>\n<p class=\"wp-block-paragraph\">In July, the Trump administration also urged U.S. AI developers to open source more <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/technology\/\" data-internallinksmanager029f6b8e52c=\"4\" title=\"Technology\" target=\"_blank\" rel=\"noopener\">technology<\/a> to promote global adoption of AI aligned with American values.<\/p>\n<div class=\"wp-block-techcrunch-inline-cta\">\n<div class=\"inline-cta__wrapper\">\n<p>Techcrunch event<\/p>\n<div class=\"inline-cta__content\">\n<p>\n\t\t\t\t\t\t\t\t\t<span class=\"inline-cta__location\">San Francisco<\/span><br \/>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"inline-cta__separator\">|<\/span><br \/>\n\t\t\t\t\t\t\t\t\t\t\t\t\t<span class=\"inline-cta__date\">October 27-29, 2025<\/span>\n\t\t\t\t\t\t\t<\/p>\n<\/p><\/div>\n<\/p><\/div>\n<\/div>\n<p class=\"wp-block-paragraph\">With the release of gpt-oss, OpenAI hopes to curry favor with developers and the Trump administration alike, both of which have watched the Chinese AI labs rise to prominence in the open source space.<\/p>\n<p class=\"wp-block-paragraph\">\u201cGoing back to when we started in 2015, OpenAI\u2019s mission is to ensure AGI that benefits all of humanity,\u201d said Altman in a statement shared with TechCrunch. \u201cTo that end, we are excited for the world to be building on an open AI stack created in the United States, based on democratic values, available for free to all and for wide benefit.\u201d<\/p>\n<figure class=\"wp-block-image aligncenter size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" height=\"453\" width=\"680\" src=\"https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?w=680\" alt=\"Open AI CEO Sam Altman\" class=\"wp-image-2993943\" style=\"width:683px;height:auto\" srcset=\"https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg 8660w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=150,100 150w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=300,200 300w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=768,512 768w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=680,453 680w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=1200,800 1200w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=1280,853 1280w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=430,287 430w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=720,480 720w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=900,600 900w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=800,533 800w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=1536,1024 1536w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=2048,1365 2048w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=668,445 668w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=562,375 562w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=925,617 925w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=708,472 708w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/04\/GettyImages-2197366846.jpg?resize=50,33 50w\" sizes=\"auto, (max-width: 680px) 100vw, 680px\"\/><figcaption class=\"wp-element-caption\"><span class=\"wp-block-image__credits\"><strong>Image Credits:<\/strong>Tomohiro Ohsumi \/ Getty Images<\/span><\/figcaption><\/figure>\n<h2 class=\"wp-block-heading\" id=\"h-how-the-models-performed\"><span class=\"ez-toc-section\" id=\"How_the_models_performed\"><\/span>How the models performed<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"wp-block-paragraph\">OpenAI aimed to make its open model a leader among other open-weight AI models, and the company claims to have done just that. <\/p>\n<p class=\"wp-block-paragraph\">On Codeforces (with tools), a competitive coding test, gpt-oss-120b and gpt-oss-20b score 2622 and 2516, respectively, outperforming DeepSeek\u2019s R1 while underperforming o3 and o4-mini.<\/p>\n<figure class=\"wp-block-image size-large is-resized\"><img loading=\"lazy\" decoding=\"async\" height=\"459\" width=\"680\" src=\"https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?w=680\" alt=\"\" class=\"wp-image-3034265\" style=\"width:680px;height:auto\" srcset=\"https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png 1232w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=150,101 150w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=300,203 300w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=768,519 768w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=680,459 680w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=1200,810 1200w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=430,290 430w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=720,486 720w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=900,608 900w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=800,540 800w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=668,451 668w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=555,375 555w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=914,617 914w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=708,478 708w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.21.54PM.png?resize=50,34 50w\" sizes=\"auto, (max-width: 680px) 100vw, 680px\"\/><figcaption class=\"wp-element-caption\"><span class=\"wp-element-caption__text\">OpenAI\u2019s open model performance on codeforces.<\/span><span class=\"wp-block-image__credits\"><strong>Image Credits:<\/strong>OpenAI<\/span><\/figcaption><\/figure>\n<p class=\"wp-block-paragraph\">On Humanity\u2019s Last Exam (HLE), a challenging test of crowdsourced questions across a variety of subjects (with tools), gpt-oss-120b and gpt-oss-20b score 19% and 17.3%, respectively. Similarly, this underperforms o3 but outperforms leading open models from DeepSeek and Qwen.<\/p>\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" height=\"438\" width=\"680\" src=\"https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?w=680\" alt=\"\" class=\"wp-image-3034259\" srcset=\"https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png 1272w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=150,97 150w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=300,193 300w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=768,495 768w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=680,438 680w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=1200,774 1200w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=430,277 430w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=720,464 720w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=900,580 900w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=800,516 800w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=668,431 668w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=582,375 582w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=957,617 957w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=708,456 708w, https:\/\/techcrunch.com\/wp-content\/uploads\/2025\/08\/Screenshot-2025-08-05-at-12.18.20PM.png?resize=50,32 50w\" sizes=\"auto, (max-width: 680px) 100vw, 680px\"\/><figcaption class=\"wp-element-caption\"><span class=\"wp-element-caption__text\">OpenAI\u2019s open model performance on HLE.<\/span><span class=\"wp-block-image__credits\"><strong>Image Credits:<\/strong>OpenAI<\/span><\/figcaption><\/figure>\n<p class=\"wp-block-paragraph\">Notably, OpenAI\u2019s open models hallucinate significantly more than its latest AI reasoning models, o3 and o4-mini. <\/p>\n<p class=\"wp-block-paragraph\">Hallucinations have been getting more severe in OpenAI\u2019s latest AI reasoning models, and the company previously said it doesn\u2019t quite understand why. In a white paper, OpenAI says this is \u201cexpected, as smaller models have less world knowledge than larger frontier models and tend to hallucinate more.\u201d<\/p>\n<p class=\"wp-block-paragraph\">OpenAI found that gpt-oss-120b and gpt-oss-20b hallucinated in response to 49% and 53%, respectively, of questions on PersonQA, the company\u2019s in-house benchmark for measuring the accuracy of a model\u2019s knowledge about people. That\u2019s more than <a href=\"https:\/\/buradabiliyorum.com\/en\/category\/trip-and-travel\/\" data-internallinksmanager029f6b8e52c=\"10\" title=\"Trip &amp; Travel\" target=\"_blank\" rel=\"noopener\">trip<\/a>le the hallucination rate of OpenAI\u2019s o1 model, which scored 16%, and higher than its o4-mini model, which scored 36%.<\/p>\n<h2 class=\"wp-block-heading\" id=\"h-training-the-new-models\"><span class=\"ez-toc-section\" id=\"Training_the_new_models\"><\/span>Training the new models<span class=\"ez-toc-section-end\"><\/span><\/h2>\n<p class=\"wp-block-paragraph\">OpenAI says its open models were trained with similar processes to its proprietary models. The company says each open model leverages mixture-of-experts (MoE) to tap fewer parameters for any given question, making it run more efficiently. For gpt-oss-120b, which has 117 billion total parameters, OpenAI says the model only activates 5.1 billion parameters per token.<\/p>\n<p class=\"wp-block-paragraph\">The company also says its open model was trained using high-compute reinforcement learning (RL) \u2014 a post-training process to teach AI models right from wrong in simulated environments using large clusters of Nvidia GPUs. This was also used to train OpenAI\u2019s o-series of models, and the open models have a similar chain-of-thought process in which they take additional time and computational resources to work through their answers.<\/p>\n<p class=\"wp-block-paragraph\">As a result of the post-training process, OpenAI says its open AI models excel at powering AI agents and are capable of calling tools such as web search or Python code execution as part of its chain-of-thought process. However, OpenAI says its open models are text-only, meaning they will not be able to process or generate images and audio like the company\u2019s other models.<\/p>\n<p class=\"wp-block-paragraph\">OpenAI is releasing gpt-oss-120b and gpt-oss-20b under the Apache 2.0 license, which is generally considered one of the most permissive. This license will allow enterprises to monetize OpenAI\u2019s open models without having to pay or obtain permission from the company. <\/p>\n<p class=\"wp-block-paragraph\">However, unlike fully open source offerings from AI labs like AI2, OpenAI says it will not be releasing the training data used to create its open models. This decision is not surprising given that several active lawsuits against AI model providers, including OpenAI, have alleged that these companies inappropriately trained their AI models on copyrighted works.<\/p>\n<p class=\"wp-block-paragraph\">OpenAI delayed the release of its open models several times in recent months, partially to address safety concerns. Beyond the company\u2019s typical safety policies, OpenAI says in a white paper that it also investigated whether bad actors could fine-tune its gpt-oss models to be more helpful in cyberattacks or the creation of biological or chemical weapons.<\/p>\n<p class=\"wp-block-paragraph\">After testing from OpenAI and third-party evaluators, the company says gpt-oss may marginally increase biological capabilities. However, it did not find evidence that these open models could reach its \u201chigh capability\u201d threshold for danger in these domains, even after fine-tuning.<\/p>\n<p class=\"wp-block-paragraph\">While OpenAI\u2019s model appears to be state-of-the-art among open models, developers are eagerly awaiting the release of DeepSeek R2, its next AI reasoning model, as well as a new open model from Meta\u2019s Superintelligence Lab.<\/p>\n<\/div>\n<blockquote><p><strong><span style=\"color: #ff6600;\">If you liked the article, do not forget to share it with your friends. Follow us on\u00a0<span style=\"color: #ff0000;\"><a style=\"color: #ff0000;\" href=\"https:\/\/news.google.com\/publications\/CAAqBwgKMN63nwsw68G3Aw\" target=\"_blank\" rel=\"nofollow noopener noreferrer\">Google News<\/a><\/span>\u00a0too, click on the star and choose us from your favorites.<\/span><\/strong><\/p><\/blockquote>\n<blockquote>\n<p style=\"text-align: center;\"><strong>If you want to read more like this article, you can visit our <span style=\"color: #ff9900;\"><a style=\"color: #ff9900;\" href=\"https:\/\/buradabiliyorum.com\/en\/category\/technology\/\" target=\"_blank\" >Technology<\/a><\/span> category.<\/strong><\/p>\n<\/blockquote>\n<p><span style=\"color: black;\"><a style=\"color: #ff9900;\" href=\"https:\/\/techcrunch.com\/2025\/08\/05\/openai-launches-two-open-ai-reasoning-models\/\" target=\"_blank\" >Source<\/a><\/span><\/p>\n","protected":false},"excerpt":{"rendered":"<p>OpenAI announced Tuesday the launch of two open-weight AI reasoning models with similar capabilities to its o-series. Both are freely available to download from the online developer platform Hugging Face, the company said, describing the models as \u201cstate of the art\u201d when measured across several benchmarks for comparing open models. The models come in two&#8230;<\/p>\n","protected":false},"author":1,"featured_media":683525,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"fifu_image_url":"https:\/\/techcrunch.com\/wp-content\/uploads\/2024\/12\/GettyImages-2021258442.jpg?resize=1200,800","fifu_image_alt":"","footnotes":""},"categories":[18],"tags":[77337,157602,141199],"class_list":["post-683524","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-technology","tag-ai","tag-open-model","tag-openai"],"_links":{"self":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/683524","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/comments?post=683524"}],"version-history":[{"count":0,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/posts\/683524\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media\/683525"}],"wp:attachment":[{"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/media?parent=683524"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/categories?post=683524"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/buradabiliyorum.com\/en\/wp-json\/wp\/v2\/tags?post=683524"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}