uRun is a company that provides the infrastructure layer for interactive generative AI. Its core offering is real-time, stateful inference at scale, a technical capability essential for applications requiring continuous creation across sessions and streams. The company's primary product is the Inference Cloud Platform, a compute layer that delivers this functionality via APIs.
The company operates within the generative AI infrastructure sector, serving model labs and research teams. Its technical domains include real-time inference, stateful inference, and AI video generation. uRun emerged from stealth and is backed by top-tier investors, with leadership possessing deep expertise in scaling inference infrastructure.
