TECHNOLOGY · VERIFIED DEVELOPMENT
OpenAI Launches Ultrafast API Tier, Boosting GPT‑5.6 Sol Speed 14‑Fold
WHY IT MATTERS
The 14‑fold speed boost and 750‑token‑per‑second rate enable developers to build faster, more responsive AI applications, opening new possibilities for real‑time services and improving user experience.
What happened
OpenAI has unveiled a preview of its new Ultrafast API service tier, which runs the GPT‑5.6 Sol model up to fourteen times faster than previous offerings. Powered by Cerebras’ hardware, the tier can deliver up to 750 output tokens per second, a significant jump in throughput for developers and businesses that rely on rapid text generation. The upgrade promises lower latency and higher capacity for real‑time applications, while maintaining the same model capabilities as standard GPT‑5.6 Sol.
The move positions OpenAI to better serve high‑volume use cases, such as instant translation, live chatbots, and dynamic content creation, where speed is critical.
DEVELOPING STORY
Story timeline
PRIMARY SOURCES
Previewing Ultrafast mode: GPT-5.6 Sol at up to 14X the speed
OpenAI (company statement) · Corporate primary source; facts only, no copied text or images; link and attribution required