OpenAI has introduced its first artificial intelligence chip, called Jalapeño, marking a major milestone in the company’s effort to build more of the technology powering its AI services. Developed in partnership with Broadcom, the chip is designed primarily for AI inference, the process of running AI models and generating responses for users across ChatGPT and other applications.
OpenAI Expands Beyond Nvidia
OpenAI has relied heavily on Nvidia’s graphics processing units (GPUs) to train and run its AI models. However, the rapid growth in demand for AI services has pushed the company to look for additional computing infrastructure.
Read More | Why Is Everyone Talking About OpenAI’s Images 2.0 Model?
Designed in Just Nine Months
According to OpenAI, Jalapeño was designed from the ground up in just nine months. President Greg Brockman said the company’s own AI models played a significant role in accelerating the development process. “The degree to which our models have been able to accelerate it was very surprising to us,” he said. The companies revealed that a physical sample of the chip was scheduled to be delivered to OpenAI, with initial deployment expected by the end of 2026.
What Makes Jalapeño Different?
Jalapeño is an application-specific integrated circuit (ASIC), a type of chip built for particular tasks rather than general-purpose computing. Unlike Nvidia’s GPUs, which can handle a wide range of AI workloads, ASICs are designed to perform specific functions more efficiently and at lower cost. OpenAI and Broadcom believe this approach will help improve the speed and affordability of AI services.
Read More | OpenAI Quietly Buys AI Voice Cloning Startup Weights.gg
The companies are branding the chip as an “Intelligence Processor” and describe it as the first AI accelerator in a broader platform aimed at making advanced AI systems faster, more reliable, and more accessible.
Part of a Larger Infrastructure Strategy
The launch of Jalapeño is the latest step in OpenAI’s broader plan to gain greater control over the infrastructure behind its AI models. In October, OpenAI and Broadcom disclosed plans to develop and deploy racks of OpenAI-designed chips, with an ambitious long-term goal of building enough computing capacity to require up to 10 gigawatts of power.
Read More | OpenAI Launches ChatGPT for PowerPoint: Create AI Presentation Slides With Simple Prompts
OpenAI has also diversified its hardware partnerships in recent months. Earlier this year, the company signed an agreement with Amazon Web Services (AWS) to use its Trainium AI chips. It has also partnered with AMD and AI chipmaker Cerebras as it expands beyond Nvidia-based infrastructure.
Indrani Priyadarshini is a journalist and editorial professional specialising in technology, artificial intelligence, smart cities, green energy, and digital transformation. With over four years of experience in tech journalism and digital media, she is known for turning complex industry developments into clear, engaging, and insightful stories. Her expertise spans reporting, editorial strategy, digital publishing workflows, and in-depth coverage of emerging technologies shaping the future. She has also conducted high-profile interviews and podcasts with industry leaders, bringing sharp analysis and accessible storytelling to a wide audience.
