Saturn Cloud Partners With Lilac to Bring Enterprise GPU Capacity Into Its Token Factory Platform

The partnership adds Lilac as a capacity provider for Saturn Cloud’s token factory platform, giving GPU cloud operators and enterprises a path to model serving and per-token inference on capacity that is already powered on.

Saturn Cloud, the AI token factory platform, announced a partnership with Lilac, a Y Combinator-backed inference provider that routes workloads to idle enterprise GPUs. Under the agreement, Saturn Cloud has selected Lilac as a GPU network provider for its platform, extending the supply available to GPU cloud operators and enterprises for model serving and per-token inference.

Lilac draws on NVIDIA AI infrastructure that is already powered on and paid for, and makes it available for inference through an OpenAI-compatible API. That keeps utilization high on hardware the enterprise already owns and pricing low on the consumption side. For Saturn Cloud customers, it means more GPUs to run inference on without standing up new hardware, priced per token with no reserved commitments.

Also Read: CIO Influence Interview with Hugo Dozois-Caouette, CTO and Co-founder at MaintainX

“Operators want every usable GPU hour working, and a lot of capacity sits idle inside enterprises that never reaches the teams who need it. Selecting Lilac as a provider lets us route token factory workloads to that capacity, so customers get serving and per-token inference without waiting on new infrastructure,” said Sebastian Metti, Founder of Saturn Cloud.

The fit is variable inference demand, which is costly to serve on reserved hardware. A Saturn Cloud customer can point a serving workload at Lilac capacity, scale it up as traffic rises, and release it when demand falls. For operators, that means offering inference to their tenants without carrying reserved GPUs themselves. For enterprises, it means serving models without a standing hardware commitment.

“The industry’s GPU problem is often a utilization problem: valuable infrastructure sits idle while inference teams are asked to reserve even more capacity,” said Lucas Ewing, co-founder of Lilac. “Saturn Cloud turns GPU infrastructure into a complete token factory, and Lilac expands the capacity that factory can draw from.”