[CLSTR]
< Back to situation

[REVISION HISTORY]

OpenAI development of Jalapeño AI inference chip

Updated 1 time since CLSTR started tracking revisions of this situation.

What changed

2026-08-27 20:01 UTC → 2026-08-29 04:59 UTC · added removed

OpenAI has announced the development of Jalapeño, a unveiled performance data for its custom AI inference chip created chip, Jalapeño, developed in collaboration with Broadcom and Celestica. The hardware is Designed specifically designed to handle large language model (LLM) workloads, aiming workloads rather than model training, the hardware aims to lower computing costs and reduce the company’s dependency on Nvidia hardware. Technical specifications indicate the chip utilizes a single die based on TSMC’s 3nm process, featuring 216 GiB of HBM4 memory and 13.4 PFLOPs of compute. Benchmark data suggests testing conducted via SemiAnalysis’ InferenceX tool indicates that the chip outperforms Nvidia’s GB200 and GB300 systems, delivering systems. Specifically, Jalapeño reportedly delivers between 1.5 and 1.9 times more AI work per watt and reducing latency by achieves 1.7 to 3.6 times. times lower latency. For interactive AI agent workloads, performance gains may reach up to 4.1 times. Technical specifications note the chip utilizes a single die based on TSMC’s 3nm process, featuring 216 GiB of HBM4 memory and 13.4 PFLOPs of compute. While the chip is rated at 700 watts, testing showed actual power draw remained at or below 550 watts. OpenAI reportedly used utilized its own AI models to assist in the design and circuit verification process, which shortened the development cycle from concept to tapeout to nine months. Small-scale deployment of the chip is expected to begin by the end of 2026, with a full production ramp anticipated between 2027 and 2028. While Jalapeño focuses on inference, OpenAI intends to continue using Nvidia and other partners for model training.

Versions

  1. 2026-08-29 04:59 UTC OpenAI development of Jalapeño AI inference chip
  2. 2026-08-27 20:01 UTC OpenAI development of Jalapeño AI inference chip

Only revisions since CLSTR began indexing content versions appear here. Select a version to see what changed compared to the one before it.