Wall St Engine(@wallstengine):Cerebras $CBRS is powering a new “Ultrafast” tier for OpenAI’s GPT-5.6 Sol, delivering up to 750 tokens/sec, or as much as 14x faster than standard processing. The tier is in limited preview for OpenAI API customers and uses Cerebras’ wafer-scale architecture with 44GB of on-chip SRAM. On GDP-Val, OpenAI says it delivered a 5.6x end-to-end speedup with no reported loss in quality.

Wall St Engine

@wallstengine

Fast, accurate, consistent stock market news, earnings highlights & more. By Brillinsight. Not financial advice.

加入 March 2022

974 正在關注 196.6K 粉絲

Wall St Engine@wallstengine

2026.08.13 17:05

Cerebras $CBRS is powering a new “Ultrafast” tier for OpenAI’s GPT-5.6 Sol, delivering up to 750 tokens/sec, or as much as 14x faster than standard processing. The tier is in limited preview for OpenAI API customers and uses Cerebras’ wafer-scale architecture with 44GB of on-chip SRAM. On GDP-Val, OpenAI says it delivered a 5.6x end-to-end speedup with no reported loss in quality.