OpenAI Unveils Fast Jalapeno AI Chip
OpenAI's new chip delivers higher speed and power efficiency. It enables faster AI responses.

OpenAI has announced the results of testing its first custom inference chip, Jalapeno. The chip delivers higher throughput, lower latency, and greater power efficiency across multiple AI models.
OpenAI CEO Sam Altman announced the development on social media, saying 'we made a chip and it is fast'. The company has been testing Jalapeno and the system around it, and the results show a major advance in AI inference.
According to OpenAI, Jalapeno can serve more AI work per unit of power while also returning responses more quickly. The chip delivers both higher throughput and lower latency with one architecture, where existing hardware systems often have to make a tradeoff between the two.
The company said the chip could enable faster responses, more responsive agents, and more reliable access as demand grows. The gains could make increasingly capable AI more affordable and more broadly available.
Jalapeno's performance was tested across several models, including GPT-OSS 120B, DeepSeek R1, and Kimi K2.5 1T. The chip delivered 1.5 to 1.9 times more AI work per watt at peak throughput and 1.7 to 3.6 times lower end-to-end latency than the comparison systems.
For highly interactive workloads, Jalapeno delivered 2.1 to 4.1 times higher performance. The chip was evaluated using InferenceX, a public benchmark from SemiAnalysis that measures the full process of serving an AI request.
OpenAI compared Jalapeno with leading commercially available AI systems across operating conditions ranging from high-throughput serving to highly interactive, low-latency use. The company said Jalapeno is rated at 700 watts, while its measured sustained power remained at or below 550 watts on the tested workloads.
Jalapeno represents a broader 'full-stack advantage' for OpenAI, allowing the company to design models, products, serving software, chips, memory, networking, and systems together. The chip is the beginning of a multigenerational platform.
The development of Jalapeno is a significant step forward for OpenAI and the AI industry as a whole. It has the potential to enable more efficient and effective AI systems, which could have a major impact on a wide range of applications and industries.
In the future, we can expect to see further advancements in AI chip technology, which will continue to drive innovation and improvement in the field. OpenAI's Jalapeno chip is an important milestone in this journey, and it will be interesting to see how it is used and developed in the coming years.
The significance of Jalapeno cannot be overstated. It has the potential to revolutionize the way AI systems are designed and deployed, and it could have a major impact on the future of the AI industry. As AI continues to play an increasingly important role in our lives, the development of efficient and effective AI chips like Jalapeno will be crucial to driving progress and innovation in the field.
Frequently asked questions
What is Jalapeno?
Jalapeno is OpenAI's first custom inference chip, which delivers higher throughput, lower latency, and greater power efficiency across multiple AI models.
How does Jalapeno compare to other AI systems?
Jalapeno delivered 1.5 to 1.9 times more AI work per watt at peak throughput and 1.7 to 3.6 times lower end-to-end latency than the comparison systems.