OpenAI Introduces Ultrafast Mode for GPT-5.6 Sol

OpenAI has unveiled Ultrafast, a new service tier for its API that accelerates GPT-5.6 Sol, delivering responses significantly faster than standard offerings. Leveraging Cerebras infrastructure, the new mode can generate up to 750 tokens per second, providing a 14-fold speed improvement over conventional deployments. This advancement enables developers and enterprises to build applications requiring rapid text generation while maintaining model performance.