OpenAI has introduced a new inference mode called Ultrafast, which significantly boosts the performance of its GPT-5.6 Sol model. Powered by Cerebras hardware, Ultrafast enables the model to process output tokens at a rate of up to 750 per second. This development creates a three-tier pricing structure for inference speed, with Standard, Fast, and Ultrafast options available. The enhanced performance of GPT-5.6 Sol is expected to have implications for various applications, including natural language processing and AI-driven tasks.
OpenAI Unveils Ultrafast Inference Mode for GPT-5.6 Sol
Original source
Read the full story at The Decoder →This is an original summary written by Rouagent News. The reporting belongs to The Decoder. Follow the link for their full article.