OpenAI and Broadcom tape out Jalapeño, a custom inference chip in about nine months
OpenAI and Broadcom pulled the cover off Jalapeño, OpenAI's first custom silicon — a reticle-sized ASIC built to run large models rather than train them. The companies say it went from design to manufacturing tape-out in roughly nine months, one of the fastest advanced-ASIC cycles they've seen, with OpenAI's own models pitching in on the design. Engineering samples are already running lab workloads including a GPT-5.3 Codex variant, with performance-per-watt claimed well above current state of the art, as the first step in a multi-generation OpenAI-Broadcom-Celestica platform slated to start deploying by the end of 2026.
Why it matters: Designing the chip your models run on is the clearest statement yet that frontier labs no longer want to rent their entire stack. Inference — not training — is where cost compounds as usage scales, so a purpose-built inference ASIC with better performance-per-watt attacks the single biggest line item in serving models at OpenAI's volume. The nine-month cycle is the eyebrow-raiser: if using their own models to compress ASIC design timelines holds up, it hints at a flywheel where AI accelerates the hardware that makes AI cheaper. Strategically this is another pressure point on Nvidia's margins and a hedge against GPU allocation being the thing that caps a lab's growth. The caveats are real — engineering samples aren't volume production, and end-of-2026 deployment leaves ample room for slippage — but the direction of travel is unmistakable: owning silicon is becoming a frontier-lab requirement, not a luxury.