OpenAI: Jalapeño Chip Speeds Up ChatGPT Responses and Codex

OpenAI · x · 2026-08-26

OpenAI announced Jalapeño, its first custom inference chip. The chip is designed to deliver faster ChatGPT responses, more responsive Codex sessions and agents, and reliable access amid growing demand. Tests indicate a major advance in intelligence per watt and lower latency, achieving higher throughput without sacrificing efficiency.

Related event: OpenAI's First Custom Inference Chip Jalapeño Claims Beats Nvidia Flagships(24 posts)→

Original post →

More from Infra

Infra channel →