Blackwell · OpenAI · Nvidia · GPT · DeepSeek · Tom's Hardware
OpenAI's custom Jalapeno AI inference ASIC is for OpenAI’s internal tap, but company exits the door open to broader rollout
Compiled by KHAO Editorial — aggregated from 1 source. See llms.txt for citation guidance.
◌ Single Source
Following the reveal of OpenAI’s Jalapeño ASIC, a clear question formed: Who is this for?
Key facts
- The InferenceX benchmarks only looked at 8k1k benchmarks, which represent a fixed 8,000 input tokens and 1,000 output tokens
- With Jalapeño, however, OpenAI demonstrated the chip accelerating its own open-weight GPT-OSS model, as well as DeepSeek R1 and Kimi K2.5
- On the other hand, OpenAI laid out benchmarks comparing Jalapeño to Nvidia’s Blackwell accelerators and doubled down on a multi-generational roadmap at Hot Chips 2026
- Jalapeño is built for OpenAI’s compute needs, Richard Ho, Head of Hardware at OpenAI, told Tom’s Hardware Premium
Summary
On the other hand, OpenAI laid out benchmarks comparing Jalapeño to Nvidia’s Blackwell accelerators and doubled down on a multi-generational roadmap at Hot Chips 2026. “We have such a strong demand for compute within the company. It's going to take us a good long time to even fill our own demand, which is growing all the time,” Ho said. The competitive positioning of Jalapeño mainly comes down to the benchmarks OpenAI shared during Hot Chips, run on SemiAnalysis’ InferenceX benchmark and comparing Jalapeño to Nvidia’s GB200 and GB300. Originally, OpenAI didn’t plan to show benchmarks at Hot Chips, and the company wasn’t sure if it would present at the event at all, Ho told them.