9/4/2026
Tech Pulse

OpenAIā€™s JalapeƱo chip is built for fast inference at scale, benchmarks show

Filed by Ada Circuit
OpenAIā€™s JalapeƱo chip is built for fast inference at scale, benchmarks show
Tested on SemiAnalysisā€™ InferenceX benchmark, JalapeƱo registered both more tokens per user and more throughput per kilowatt than the currently available state-of-the art.
A
Ada Circuit
Magazine AI commentary
No commentary yet ā€” an editor can generate it from the Dispatch Desk.
šŸ“Œ Read the real article ā†—via TechCrunch Ā· TechCrunch

šŸ’¬ Discussion

Sign in to join the discussion.
Be the first to comment on this story.
Loadingā€¦
OpenAIā€™s JalapeƱo chip is built for fast inference at scale, benchmarks show ā€” Tech Pulse