FriendliAI, The Frontier AI Inference Cloud, has launched Friendli InferenceSense™, the industry's first inference monetization platform purpose-built for GPU cloud operators. The platform tackles a persistent and expensive reality: GPU clusters cost billions to build and operate, yet many sit idle or underutilized for large portions of every day, turning every idle GPU-hour into lost margin.
FriendliAI launched InferenceSense, a platform that detects idle GPU capacity and automatically fills it with paid AI inference workloads.
The platform operates like "AdSense for GPUs," allowing operators to monetize idle cycles while their own workloads always take priority.
FriendliAI brings a ready pool of global demand for popular open-weight models including DeepSeek, Qwen, Kimi, GLM, and MiniMax.
Token revenue generated on partner GPUs is shared between the operator and FriendliAI with no upfront fees or minimum commitments.
When a scheduler reclaims a GPU, InferenceSense gracefully vacates within seconds, ensuring production jobs are never delayed.
The platform is designed for GPU neoclouds, ML platforms, and research institutions with underutilized infrastructure.
GPU infrastructure demands massive capital outlay—a single H100 rents for approximately $2.00 per hour, with an 8-GPU node costing $16–20 per hour—yet no fleet achieves 100% utilization. Training jobs are inherently bursty: they complete, and the hardware goes dark until the next run. Even fully-committed neoclouds experience idle windows between customer workloads. Every idle GPU-hour represents lost margin.
"The modern data center isn't just a massive compute cluster—it is an AI factory, a high-performance production environment built to manufacture intelligence at scale. Yet most GPU operators act like traditional landlords, watching revenue evaporate every time a workload finishes, or a contract ends," said Byung-Gon Chun, CEO of FriendliAI. "The industry is building these massive factories, but most GPU clouds are still missing the inference assembly line that actually transforms raw compute into tokens—the true finished goods of this era. InferenceSense provides that missing assembly line. Every idle GPU-hour becomes a chance to serve real AI demand and capture token revenue. We own the demand pipeline, the optimization, and the serving—our partners simply plug in and earn. The AI factory build-out only makes sense when it actually makes cents."
When InferenceSense detects available GPU capacity, it spins up secured, fully-isolated containers that serve paid AI inference workloads. Under the hood, FriendliAI's inference engine maximizes token throughput per GPU-hour, squeezing peak economic value from every idle cycle. The moment a scheduler reclaims a GPU, InferenceSense's preemption controller gracefully terminates the monetized workload and returns the hardware within seconds—zero downtime, zero disruption, zero config changes.
Integration is frictionless. Operators retain full control—choosing which nodes participate, setting time-of-day schedules, and defining exactly how much spare capacity InferenceSense may use. Demand is built in; there is no need to source inference customers independently. FriendliAI brings a ready pool of global demand for widely-used open-weight models including DeepSeek, Qwen, Kimi, GLM, and MiniMax, and dispatches workloads to partner hardware automatically.
The prevailing GPU cloud model charges by the hour. Between customer workloads, revenue drops to zero—but the cost of power, cooling, and depreciation never stops. InferenceSense converts that dead time into an incremental revenue stream.
The mechanics are straightforward: FriendliAI aggregates global, real-time demand for popular open-weight models and routes paid inference workloads to partner GPUs. Partners earn a share of the token revenue generated during otherwise-empty hours. FriendliAI owns the demand pipeline, model optimization, and serving stack; the partner contributes idle capacity.
Because token generation scales with computational efficiency, monetized inference workloads can generate significantly higher economic yield per GPU-hour than traditional rental models. There is no upfront cost and no minimum commitment. If a GPU is idle, it earns. The moment workloads need it back, InferenceSense yields instantly.
InferenceSense is designed for any organization operating GPU-dense infrastructure—GPU neoclouds, ML platforms, and research institutions. Any operator whose GPUs are not fully utilized around the clock is a candidate.
Get Started
Friendli InferenceSense™ is now accepting applications from qualified GPU cloud operators. To explore how InferenceSense can unlock new revenue from your existing infrastructure, contact partners@friendli.ai to schedule an executive briefing during NVIDIA GTC.
About FriendliAI
FriendliAI is The Frontier AI Inference Cloud. Built by the researchers who invented the continuous batching technique that is now industry standard, FriendliAI provides AI engineers with a highly optimized engine that constantly evolves to efficiently run state-of-the-art open-weight and custom models at production scale. By maximizing GPU utilization, FriendliAI delivers speeds up to 3x faster than vLLM, and 50% to 90% cost savings relative to closed model APIs. FriendliAI empowers engineers to deploy frontier AI with uncompromising speed, model ownership, and enterprise-grade reliability.
TechIntelPro empowers B2B technology decision-makers with the latest industry trends, deep insights, leadership perspectives and actionable intelligence to drive both organizational and professional milestones—and thrive on the tech pulse.