Cerebras powers OpenAI Ultrafast mode for GPT-5.6 Sol

Cerebras said it powers an Ultrafast service tier for OpenAI's GPT-5.6 Sol model, which is in limited preview for OpenAI customers. The release claims up to 750 output tokens per second and up to 14 times the speed of standard processing. OpenAI is named as a launch partner for the model, which supports the premium-speed revenue case for Cerebras cloud.

• Powers Ultrafast mode for OpenAI GPT-5.6 Sol
• Claimed up to 750 output tokens per second
• Up to 14 times faster than standard processing
• Initially in limited preview for OpenAI customers