OpenAI reveals Jalapeno its first AI processor
Custom inference silicon could loosen Nvidia's grip on AI compute and push down the cost of running AI.
Key takeaways
- OpenAI has revealed Jalapeño, an AI inference chip it designed with Broadcom to power current and future large language models.
- Jalapeño is an ASIC built for inference, the work of answering requests in tools like ChatGPT and Codex, rather than training.
- Broadcom CEO Hock Tan says it matches the performance of Nvidia's Blackwell chips and Google's Tensor processing units.
- OpenAI calls it the first step in a multi-generation compute platform and expects to deploy it by the end of 2026.
Cite or link to this article
Griffin, M. (2026) 'OpenAI reveals Jalapeno its first AI processor', 311 Institute, 24 June. Available at: https://www.311institute.com/openai-jalapeno-ai-inference-chip/ (Accessed: 25 October 2026).
OpenAI has just revealed a new “intelligence processor” chip for Artificial Intelligence (AI) servers made in partnership with Broadcom. The chip, called Jalapeño, is designed to power current and future Large Language Models, according to an announcement on Wednesday.
The Future and Deep Future of AI 2040, a keynote by futurist Matthew Griffin
Jalapeño is an ASIC (Application-Specific Integrated Circuit), meaning it’s designed for a specific purpose: AI inference. With AI inference, models process a user’s 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.
It comes just nine months after OpenAI revealed that it would team up with Broadcom to make its own chips, helping reduce the company’s reliance on the GPUs offered by Nvidia that are in limited supply. In an interview with Reuters, Broadcom CEO Hock Tan says it matches the performance of Nvidia’s Blackwell chips and Google’s Tensor processing units. Microsoft, Meta, and Amazon 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’s chips on overall performance.
OpenAI calls Jalapeño the “first step in a multi-generation compute platform,” which it expects to deploy by the end of 2026.
“While OpenAI is still measuring final performance, early testing shows that Jalapeño will deliver performance per watt substantially better than current state-of-the-art,” OpenAI says.
First published on Fanatical Futurist on 24 June 2026.
311 Intelligence
What this means
Analysis by the 311 Strategic Intelligence Unit
The big shift is from buying AI chips to designing them. OpenAI joins Microsoft, Meta, Amazon and Google in building its own silicon, and Jalapeño is aimed at inference, the everyday work of answering requests, rather than training. Our Starburst data shows why that matters now: we rate AI Inference Cost Collapse, the price of running AI at a given quality falling roughly tenfold or more each year for most tasks, an Act now trend, and Neural Processing Units, chips built to speed up neural networks, already reached wide use in 2025.
What it means by sector.
- Technology and cloud: chips designed for one company's own models put pressure on Nvidia, whose GPUs OpenAI says are in limited supply. Broadcom's claim that Jalapeño matches Blackwell and Google's Tensor processing units, if it holds, gives the largest AI buyers more bargaining power.
- Every organisation using AI: OpenAI says early testing shows performance per watt substantially better than the current state of the art. Cheaper, more efficient inference is one of the forces we track behind the falling cost of AI services.
- Governments: we track Technological Sovereignty, efforts to cut reliance on foreign chips, cloud and software, as an Act now trend, and the AI Compute Divide, computing power concentrating in a few countries, as a Prepare trend. Custom chips from a handful of US firms add to that concentration.
What to do now.
- Separate your AI spending into training and inference, and expect inference prices to keep falling as custom chips arrive.
- Avoid locking long contracts to one chip supplier while new inference silicon from OpenAI, Amazon, Google, Meta and Microsoft comes to market.
- Track performance per watt, not just raw speed, when you compare AI services: energy is becoming the limiting cost.
The Starburst technologies behind this story
From the 311 Technology Starburst (first product, expected wide use and readiness):
| Technology | Category | First product | Wide use | Action | TRL |
|---|---|---|---|---|---|
| Neural Processing Units | Compute | 2017 | 2025 | Act now | 9 |
| Chiplets | Compute | 2017 | 2028 | Prepare | 9 |
| Prefill-Only Inference Chips | Compute | 2026 | 2029 | Prepare | 6 |
| Hardwired AI Model Chips | Compute | 2026 | 2030 | Prepare | 6 |
And the trends they feed, from the 311 Trends Starburst:
| Trend | Wide use | Action |
|---|---|---|
| AI Inference Cost Collapse | 2026 | Act now |
| Technological Sovereignty | 2027 | Act now |
| AI Compute Divide | 2028 | Prepare |
How this moves the trend
The race to custom AI silicon is a decade old. Google started making its own custom AI chips in 2016, and OpenAI first ordered neuromorphic AI chips from a start-up in 2024. Meanwhile Nvidia has kept raising the bar, with its CEO claiming its new AI chips are beating Moore's Law. Jalapeño is the moment OpenAI moves from customer to chip designer.
Go deeper with 311
- The 311 Starburst Centre: every technology and trend above, with timelines and readiness.
- 311 Vantage: ask what custom AI chips mean for your organisation and get a plain English executive brief.
- The Exponential Technology Codex and the Annual Trends Codex: the technologies and trends reshaping every industry.
- Book a briefing or keynote on the future of AI and computing for your board or leadership team.
FAQ
What is OpenAI's Jalapeño chip?
Jalapeño is OpenAI's first AI processor, an application-specific integrated circuit made with Broadcom. It is built for AI inference, the work of processing user requests in tools like ChatGPT and Codex, and OpenAI calls it the first step in a multi-generation compute platform.
Why is OpenAI building its own AI chips?
Making its own chips helps OpenAI reduce its reliance on Nvidia's GPUs, which are in limited supply. Microsoft, Meta and Amazon have also launched custom-designed AI chips to power their servers.
How does Jalapeño compare with Nvidia's chips?
Broadcom CEO Hock Tan told Reuters that Jalapeño matches the performance of Nvidia's Blackwell chips and Google's Tensor processing units. OpenAI says early testing shows performance per watt substantially better than the current state of the art, though final performance is still being measured.
When will OpenAI deploy Jalapeño?
OpenAI expects to deploy Jalapeño by the end of 2026, as the first generation of a multi-generation compute platform.
About the author
Matthew Griffin Founder, 311 Institute
Matthew Griffin is a multi-award winning Futurist and expert in Disruption and Innovation, Geopolitics, Leadership, and Technology, who NASA have described as a "walking encyclopaedia of the future" and a "futurist Polymath."
Read full bio
Matthew Griffin is a multi-award winning Futurist and expert in Disruption and Innovation, Geopolitics, Leadership, and Technology, who NASA have described as a "walking encyclopaedia of the future" and a "futurist Polymath." 15-time best selling author of the "Codex of the Future" series, Matthew is the Founder and Futurist in Chief of the 311 Institute, a global Futures and Deep Futures advisory firm working with royal households, world leaders, G7, G20, and G77 governments, NGOs, and multi-national mid and mega cap firms to help them explore, shape, and lead the next 50 years of business and society.
An award-winning YouTube creator with over a million followers, with an unrivalled global reach and impact, Matthew is a highly sought-after international keynote speaker, lecturer, and mentor who collaborates with global leaders through the United Nations Alliance of Civilizations (UNAOC) and United Nations General Assembly (UNGA) to shape pivotal initiatives such as the UN’s AI for Humanity program, the United Nations Conference of the Parties (UN COP), and the World Economic Forum in Davos.
As the former Global Head of Cloud, National Security, and Enterprise Sales for companies including Atos, Dell-EMC, and IBM, Matthew has a proven track record of building multi-billion dollar business units and turning failing divisions into market leaders. His ability to identify, analyse, and communicate the implications of hundreds of emerging technologies and trends is unparalleled, and his insights are trusted by many of the world’s most respected organisations, including ABB, Accenture, Adidas, AON, ARM, BCG, Centrica, Citi, Coca-Cola, Dentons, Deloitte, Dow Jones, EY, Google, KPMG, Lego, Legal & General, LinkedIn, Microsoft, PepsiCo, Qualcomm, RWE, Samsung, Siemens AG and Siemens Energy, T-Mobile, UBS, VISA, Walmart, Workday, Worldpay and many others.
Regularly featured in the global media including the AP, BBC, Bloomberg, CNBC, Discovery, Forbes, Khaleej Times, Telegraph, TIME, ViacomCBS, WIRED, and the WSJ, Matthews mission is to help organisations create a fair and sustainable future whose benefits are shared by everyone irrespective of their ability, background, or circumstances.
What future do you need to see?
Choose one to get started on computing and the future of your organisation.