OpenAI Jalapeño: Better than Nvidia Blackwell
- ID
- 17940
- Status
- summarized
- Published
- 25 Aug 2026, 10:06 PM
- Fetched
- 27 Aug 2026, 2:22 PM
- Provider
- Hacker News
- Category
- dev-community
- Original URL
- https://newsletter.semianalysis.com/p/openai-jalapeno-better-than-nvidia
- Source URL
- https://hnrss.org/best
Summary
- Score
- 7.5
- Created
- 27 Aug 2026, 2:23 PM
- Tags
- Audience
- developersai_ml_learnerssaas_founders
What happened
SemiAnalysis benchmarked OpenAI's custom inference ASIC 'Jalapeño,' designed with Broadcom from scratch in ~16 months starting mid-2024, and found it beats Nvidia Blackwell, AMD, and Google chips on performance-per-watt across multiple open-source models using HBM4. Notably, it's a generalized inference chip rather than one specialized for OpenAI's own models, and it achieves these results without Multi Token Prediction while competitors use it. OpenAI even ported Doom to the chip using Codex prompts as a demonstration.
Why it matters
If OpenAI's inference costs drop materially on custom silicon that outperforms Nvidia's flagship GPUs per watt, expect downward pressure on API pricing and a shift in who controls the AI infrastructure stack. Founders building AI products should factor in likely continued declines in inference costs when planning unit economics, and developers should watch whether OpenAI passes these savings through or uses them to widen margins.
Discussion angle
What does it mean for the GPU monopoly if a first-gen ASIC from a software company beats Nvidia's flagship on perf/watt in 16 months—and should SEA builders care about inference cost trajectories when choosing between API providers vs self-hosting?