OpenAI says its Jalapeño chip can power faster AI responses than the competition

<figure> <img alt="An image showing OpenAI’s Jalapeno chip" data-caption="" data-portal-copyright="Image: OpenAI" data-has-syndication-rights="1" src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/08/Jalapeno-chip-final.jpeg?quality=90&#038;strip=all&#038;crop=0,0,100,100" /> <figcaption> </figcaption> </figure> <p class="wp-block-paragraph">OpenAI says its new AI chip, Jalape&ntilde;o, completes tasks more efficiently and returns responses faster than other AI systems, according to a blog post published on Tuesday. During a briefing with reporters, OpenAI hardware vice president Richard Ho said Jalape&ntilde;o offers the "best of both worlds" with lower latency and higher throughput, as AI systems typically "have to make a trade-off between the two."</p> <p class="wp-block-paragraph"><a href="https://www.theverge.com/ai-artificial-intelligence/955939/openai-reveals-its-first-ai-processor-jalapeno">First introduced in June</a>, Jalape&ntilde;o is an Application-Specific Integrated Circuit (ASIC) made in partnership with Broadcom. It's designed for AI inference - the process of running a trained AI model to complete a task or deploy an agent.</p> <img src="https://platform.theverge.com/wp-content/uploads/sites/2/2026/08/tbt-jalapeno.png?quality=90&amp;strip=all&amp;crop=0,0,100,100" alt="" title="" data-has-syndication-rights="1" data-caption="&lt;em&gt;This chart measures Jalapeño&apos;s time between tokens (TBT) - or the&lt;/em&gt; &lt;em&gt;time it takes to deliver a response.&lt;/em&gt; | Image: OpenAI" data-portal-copyright="Image: OpenAI"> <p class="wp-block-paragraph">To mea …</p> <p><a href="https://www.theverge.com/ai-artificial-intelligence/984290/openai-jalapeno-ai-chip-benchmarks">Read the full story at The Verge.</a></p>