OpenAI and Broadcom announced their first custom AI chip Wednesday, a nine-month sprint that marks the ChatGPT maker's entry into silicon design and its most direct challenge yet to Nvidia's dominance in AI computing.
Called Jalapeño, the chip is an application-specific integrated circuit (ASIC) built exclusively for inference, the process of running trained AI models in response to user prompts. It is not designed for training. That distinction matters: OpenAI's $30 billion Nvidia investment from February 2026, along with an agreement to deploy 10 gigawatts of Nvidia's Vera Rubin platform, keeps the GPU giant central to the company's training pipeline.
The partnership was publicly announced in October 2025. Eight months later, the companies have a physical chip moving into data centers.
OpenAI President Greg Brockman told CNBC's David Faber that the company's own AI models accelerated the design process. "The degree to which our models have been able to accelerate it was very surprising to us," he said.
OpenAI used prior-generation models, not its cutting-edge GPT-5.5, to speed up chip development, a software-hardware feedback loop that compressed a typically multiyear process into nine months.
Early testing shows Jalapeño delivers "performance per watt substantially better than current state-of-the-art," the company said. Brockman wrote on X that "perf per watt looking incredible." OpenAI has already tested running GPT-5.3-Codex-Spark on the chip in a production workload, though in a test environment.
Broadcom is manufacturing the silicon and contributing Tomahawk networking technology. Celestica is handling board, rack, and system integration.
OpenAI plans to begin rolling out Jalapeño across active data centers by the end of this year, with more generations to follow. The chip economics are urgent. OpenAI generated $13.07 billion in revenue in 2025 but spent $34 billion, posting an operating loss of nearly $20.92 billion.
Research and development costs driven by compute infrastructure consumed $19.18 billion, roughly 56% of total spending. The company paid Microsoft over $10.59 billion for R&D and compute alone last year.
Jalapeño is OpenAI's attempt to bend that cost curve, and the timing matches a heavily anticipated public offering.
Broadcom CEO Hock Tan told CNBC that compute demand from the company's six customers is "simply insatiable." "It's just much more than we can address," he said, "and this is not just '26, not '27, we're seeing that same and even elevated demand in '28 as well."
Broadcom shares rose more than 1% Wednesday. The stock is up 10% in 2026 and has multiplied nearly sevenfold since the end of 2022.
Jalapeño joins a growing wave of custom AI silicon from Google's TPUs, Amazon's Trainium, Microsoft's Maia 200, and Meta's MTIA lineup. OpenAI is the latest software company to conclude that controlling the hardware under its models is no longer optional, it is the only path to making the math work.
"By designing more of the stack ourselves. We can serve more intelligence with greater efficiency and keep pushing advanced AI toward broader access," Brockman said in a statement.
