OpenAI unveiled its first custom-built AI chip, named Jalapeño, developed in partnership with semiconductor company Broadcom and designed to power inference workloads behind ChatGPT, Codex, the API and future agentic products.
In a post on X, OpenAI said, "We've designed and built our first AI chip: Jalapeño. Designed from the ground up by OpenAI and brought to production with @Broadcom, Jalapeño is purpose-built for the LLM workloads powering ChatGPT, Codex, the API, and future agentic products."
The company added, "Chips are foundational to the AI economy. Building our own expands our full-stack platform from products to models to infrastructure, and will help us scale intelligence, serve more people, and expand access to AI."
A physical sample of the chip was delivered to OpenAI CEO Sam Altman and President Greg Brockman by Broadcom President and CEO Hock Tan and President Charlie Kawwas.
OpenAI said the chip was designed from scratch around its understanding of LLM fundamentals, drawing on its roadmap of models, kernels, serving systems and product needs, with Broadcom and Celestica supporting industrialisation of the platform.
Engineering samples of Jalapeño are already running machine learning workloads in the lab at production target frequency and power, including GPT-5.3-Codex-Spark, though OpenAI said it is still measuring final performance.
ALSO READ: Agentic AI Is Here, 'Physical AI' To Power Next Chain Of Growth, Says Nvidia CEO
Early testing indicates the chip will deliver performance per watt substantially better than current state-of-the-art alternatives, with a detailed technical report expected in the coming months.
OpenAI said Jalapeño was co-developed from initial design to manufacturing tape-out in nine months, which it described as the fastest ASIC development cycle achieved in high-performance advanced semiconductors, aided in part by using its own models to accelerate elements of the chip's design and optimisation process.
Jalapeño marks the first chip in a multi-generation compute platform that OpenAI and Broadcom are building together, with initial deployment expected by the end of 2026 and expansion planned in the years ahead. The companies first announced their chip partnership in October, following 18 months of collaborative work.
The announcement was widely seen as a move by OpenAI to reduce its reliance on market leader Nvidia, with the companies highlighting Jalapeño's performance-per-watt advantage over current state-of-the-art chips. Broadcom shares rose more than 3% following the unveiling.
Essential Business Intelligence, Sharp Market Insights, Practical Personal Finance Advice, Daily Fuel, Gold and Silver Prices and Latest Stories — On NDTV Profit.