tech
Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed
A new speed class for frontier intelligence, turning speed into a competitive advantage.
TL;DR
- OpenAI introduces Ultrafast mode for GPT-5.6 Sol, offering significantly increased processing speed.
- The service tier runs up to 14x faster than Standard, generating up to 750 output tokens per second.
- Ultrafast is powered by Cerebras and is initially available through the OpenAI API.
- This speed improvement allows AI to be used in time-sensitive applications where intelligence was previously sacrificed for speed.
- Potential use cases include incident response, financial research, customer support, commerce, and live research.
- Early customers and OpenAI's internal teams are testing Ultrafast to understand its impact on business workflows and product development.
- The company plans to expand access as capacity grows.