OpenAI Plans to Start Deploying Jalapeno AI Chip by Year-End

05:14 AM EDT, 08/26/2026 (MT Newswires) -- OpenAI intends to begin deploying Jalapeno AI custom inference chips within its compute infrastructure by the end of 2026, the company said Tuesday. Tests so far have showed significant improvements in performance, with the chip able to conduct more AI work per unit of power and faster response times, the ChatGPT maker said. OpenAI will continue to deploy accelerators from Nvidia (NVDA) and other partners for both training and inference workloads, it said.