{"id":656957,"date":"2026-06-25T05:13:15","date_gmt":"2026-06-25T05:13:15","guid":{"rendered":"https:\/\/www.newsbeep.com\/uk\/656957\/"},"modified":"2026-06-25T05:13:15","modified_gmt":"2026-06-25T05:13:15","slug":"openai-reveals-its-first-ai-processor-jalapeno","status":"publish","type":"post","link":"https:\/\/www.newsbeep.com\/uk\/656957\/","title":{"rendered":"OpenAI reveals its first AI processor: Jalape\u00f1o"},"content":{"rendered":"<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph _1044qizi _18mzr4b1 _18mzr4b0 _19wv7tc1\">OpenAI has just revealed a new \u201cintelligence processor\u201d chip for AI servers made in partnership with Broadcom. The chip, called Jalape\u00f1o, is designed to power current and future large language models, <a href=\"https:\/\/openai.com\/index\/openai-broadcom-jalapeno-inference-chip\/\" rel=\"nofollow noopener\" target=\"_blank\">according to an announcement<\/a> on Wednesday.<\/p>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph _1044qizi _18mzr4b1 _18mzr4b0 _19wv7tc1\">Jalape\u00f1o is an ASIC (Application-Specific Integrated Circuit), meaning it\u2019s designed for a specific purpose: AI inference. With AI inference, models process a user\u2019s request to run an agent like Codex or offer a response from ChatGPT, while AI training involves a model consuming vast amounts of data to inform its responses.<\/p>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph _1044qizi _18mzr4b1 _18mzr4b0 _19wv7tc1\">It <a href=\"https:\/\/www.theverge.com\/news\/798827\/openai-broadcom-custom-ai-chips\" rel=\"nofollow noopener\" target=\"_blank\">comes just nine months<\/a> after OpenAI revealed that it would team up with Broadcom to make its own chips, helping reduce the company\u2019s reliance on the GPUs offered by Nvidia that are in limited supply. In an <a href=\"https:\/\/www.reuters.com\/world\/asia-pacific\/openai-unveils-custom-chip-it-designed-with-broadcom-boost-its-ai-infrastructure-2026-06-24\/\" rel=\"nofollow noopener\" target=\"_blank\">interview with Reuters<\/a>, Broadcom CEO Hock Tan says it matches the performance of Nvidia\u2019s Blackwell chips and Google\u2019s Tensor processing units. <a href=\"https:\/\/www.theverge.com\/2023\/11\/15\/23960345\/microsoft-cpu-gpu-ai-chips-azure-maia-cobalt-specifications-cloud-infrastructure\" rel=\"nofollow noopener\" target=\"_blank\">Microsoft<\/a>, <a href=\"https:\/\/www.theverge.com\/2024\/4\/10\/24125924\/meta-mtia-ai-chips-algorithm-training\" rel=\"nofollow noopener\" target=\"_blank\">Meta<\/a>, and <a href=\"https:\/\/www.theverge.com\/24338171\/aws-ceo-matt-garman-ai-chips-anthropic-cloud-computing-trainium-decoder-podcast-interview\" rel=\"nofollow noopener\" target=\"_blank\">Amazon<\/a> are among the other AI companies that have also launched custom-designed AI chips recently to power their servers for either training or inference, while still trailing Nvidia\u2019s chips on overall performance.<\/p>\n<p class=\"duet--article--dangerously-set-cms-markup duet--article--standard-paragraph _1044qizi _18mzr4b1 _18mzr4b0 _19wv7tc1\">OpenAI calls Jalape\u00f1o the \u201cfirst step in a multi-generation compute platform,\u201d which it expects to deploy by the end of 2026. \u201cWhile OpenAI is still measuring final performance, early testing shows that Jalape\u00f1o will deliver performance per watt substantially better than current state-of-the-art,\u201d OpenAI says.<\/p>\n","protected":false},"excerpt":{"rendered":"OpenAI has just revealed a new \u201cintelligence processor\u201d chip for AI servers made in partnership with Broadcom. The&hellip;\n","protected":false},"author":2,"featured_media":656958,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[5],"tags":[554,84,59,50,874,56,54,55],"class_list":["post-656957","post","type-post","status-publish","format-standard","has-post-thumbnail","category-business","tag-ai","tag-business","tag-gb","tag-news","tag-openai","tag-uk","tag-united-kingdom","tag-unitedkingdom"],"_links":{"self":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/656957","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/comments?post=656957"}],"version-history":[{"count":0,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/posts\/656957\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media\/656958"}],"wp:attachment":[{"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/media?parent=656957"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/categories?post=656957"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.newsbeep.com\/uk\/wp-json\/wp\/v2\/tags?post=656957"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}