cerebras powers gpt 5.6 sol to 750 tokens per second
openai's ultrafast mode hits 750 tokens per second, 14x faster than standard processing. this partnership with cerebras could revolutionize real-time enterprise ai applications.
openai unveiled ultrafast, a processing mode for its gpt 5.6 sol model that achieves 750 tokens per second, 14x the standard speed. this capability relies on a partnership with chipmaker cerebras to bypass traditional latency bottlenecks. the tool is currently in limited preview for enterprise customers in sectors like customer service and market analysis. this move prioritizes throughput over parameter count, potentially setting a new standard for ai deployment speed.