TIME Names OpenAI Jalapeño Chip a Top Invention
The custom AI inference chip earns recognition for its industry-leading performance and energy efficiency benchmarks.
Updated on Oct. 16, 2026 in Semiconductors
Live Poll
Should large tech companies prioritize designing their own hardware to improve performance and cost efficiency?
TIME has officially named OpenAI’s Jalapeño chip to its 2026 Best Inventions list following its unveiling earlier this year. Developed alongside Broadcom and Celestica, the chip is designed specifically to optimize artificial intelligence inference workloads.
Why it matters
OpenAI is pursuing custom silicon to gain greater control over AI infrastructure costs and performance. The company aims to achieve a 50 percent improvement in cost-per-token and energy efficiency compared to standard off-the-shelf components.
The chip delivers 13.4 petaflops of 4-bit compute with 232 GB of memory and 15.4 TB/s of bandwidth. It operates at 550 W sustained power, with a 700 W maximum rating.
The players
OpenAI
An artificial intelligence research organization that develops advanced large language models and supporting infrastructure.
Broadcom
A global technology company that designs, develops, and supplies a broad range of semiconductor and infrastructure software solutions.
Celestica
A multinational electronics manufacturing services company that specializes in hardware platform solutions.
Nvidia
A leading technology company that designs graphics processing units and high-performance computing hardware for artificial intelligence.
The details
Engineered for inference, the chip moved from design to tape-out in just nine months. The hardware is part of a broader collaboration between OpenAI, Broadcom, and Celestica to support large-scale AI operations.
Timeline
October 2025: OpenAI and Broadcom partnership made public.
June 24, 2026: OpenAI unveils the Jalapeño chip.
August 25, 2026: Benchmark results demonstrating efficiency gains published.
October 15, 2026: TIME names Jalapeño to Best Inventions list.
Late 2026: Small-volume deployment of the chip is scheduled.
The Tech Race
The Jalapeño chip marks a direct industry challenge to the dominance of the Nvidia H100 GPU by focusing specifically on inference efficiency. This move signals a broader transition where AI developers are bypassing standard hardware to design silicon optimized for their own proprietary models.
Increased hardware efficiency could lead to lower operational costs for AI services, potentially reducing the price of access for developers and end-users. Consumers may experience faster response times as the silicon improves the throughput of inference tasks.
The takeaway
Custom silicon represents a pivotal shift for software companies looking to control their own compute destiny. Efficiency gains like these demonstrate that hardware optimization is now as critical as algorithmic improvements for AI growth.
What happens next
Small-volume deployment is planned for late 2026, followed by a ramp to larger volumes in 2027.
Further reading
For more on the current industry landscape, visit United States Semiconductors.
Source note: This article includes information reported by Crypto Briefing.
Live Poll
Should large tech companies prioritize designing their own hardware to improve performance and cost efficiency?
