Runware launches modular Sonic Inference Pod for portable AI inference

Runware, an AI infrastructure company, announced the launch of its modular data center pod called Sonic Inference Pod. The pod is designed as a single transportable unit intended to provide flexible compute capacity alongside hyperscalers’ large-scale data center projects.

The company positions the Sonic Inference Pod as offering inference at higher quality but lower cost compared to serverless inference platforms and GPU clouds. Its modular design allows for rapid capacity expansion by deploying additional pods, rather than expanding fixed data center infrastructure.

Runware’s pods use a closed-loop cooling system and can be built and deployed in days, contrasting with traditional data centers that often take months or years to construct. The company highlights that its pods do not require water for cooling, aiming to reduce resource strain on local communities.

As of the announcement, Runware has 10 pods deployed across the U.S., Europe, and Asia-Pacific, with 160 potential sites available for future deployments. The company provides inference services to customers including Higgsfield AI and Wix.

Runware raised a $50 million Series A in December to expand its infrastructure for image generation, framing the pod initiative as part of its broader mission to supply inference capacity rather than a standalone product.

Runware’s co-founder and CEO, Flaviu Radulescu, emphasized the company’s focus on distributed compute positioned closer to end users for faster inference. He argued that this model is better suited to meet growing demand than traditional, fixed data center approaches.