OpenAI announced a custom artificial intelligence processor chip named Jalapeño on Wednesday, June 24, 2026. The company developed the chip in partnership with Broadcom.

Broadcom will manufacture the Jalapeño chips. A physical sample of the Jalapeño chip was delivered to OpenAI on the day of the announcement. OpenAI expects to deploy the chip by the end of 2026.

The Jalapeño chip is an Application-Specific Integrated Circuit (ASIC) designed for AI inference. It is intended to power current and future large language models for services such as ChatGPT and Codex. OpenAI stated that early testing shows Jalapeño delivers performance per watt that is substantially better than current state-of-the-art processors. The company also stated that it is still measuring the final performance of the Jalapeño chip.

Broadcom CEO Hock Tan stated that the Jalapeño chip matches the performance of Nvidia’s Blackwell chips and Google’s Tensor processing units. Broadcom shares climbed approximately 2% after the announcement. OpenAI described Jalapeño as the first step in a multi-generation compute platform.

OpenAI announced plans to partner with Broadcom for custom chip development in October 2025. OpenAI designed the Jalapeño chip in nine months. OpenAI also designed large parts of the computer system where the Jalapeño chip will be used. The company stated that its own AI models assisted in the development of the Jalapeño chip.

OpenAI President Greg Brockman stated that the company has a deep understanding of the workload and has been looking for specific underserved workloads to accelerate. He said that by designing more of the stack itself, OpenAI can serve more intelligence with greater efficiency and push advanced AI toward broader access. OpenAI stated it is designing the infrastructure underneath its models, including chip architecture, kernels, memory systems, networking, scheduling, deployment systems, and product experience. Microsoft, Meta, and Amazon have launched custom-designed AI chips for their servers.