OpenAI Publishes First Jalapeño Custom Inference Chip Results: Up to 1.9x Work per Watt and 3.6x Lower Latency

Key Takeaways

• ✓OpenAI officially expands into first-party silicon, publishing public model-agnostic benchmarks across open weights;
• ✓Designed around agentic serving, unified architecture handles both prefill and decode stages simultaneously;
• ✓AI-assisted chip development achieved tapeout in 9 months and enabled rapid Codex-driven model porting in 2 months.