Rent H100, H200, A100 and RTX cards from vetted data centers at a fraction of hyperscaler list price. No reservation, no annual commitment, no egress surprises.
Rates shown are per GPU per hour in USD. The market column reflects published on-demand list pricing at major cloud providers.
Operators list spare cards, you rent them by the hour. Every node is benchmarked before it goes live, and you only pay while the instance runs.
Consumer RTX cards through to multi-node H200 clusters with InfiniBand interconnect.
North America, Europe and APAC. Pin workloads to a region when data residency matters.
From clicking deploy to a running container with your image pulled and CUDA ready.
Interrupted jobs are rescheduled onto equivalent hardware automatically, at no extra cost.
Any OCI container. PyTorch, JAX and vLLM templates are one click away.
Attach NVMe storage that survives restarts and follows you across nodes.
Direct root SSH, port forwarding, and a hosted notebook on every instance.
Script provisioning, autoscale on queue depth, tear down when the run finishes.
Skip the provisioning entirely. Point an OpenAI-compatible endpoint at a dedicated model instance and pay only for the minutes it stays warm.
Single L4 or RTX 4090. Good for routing, classification and drafting.
A100 80 GB with speculative decoding enabled by default.
Dual H100 with tensor parallelism. Sustains long-context sessions.
H200 nodes with 141 GB per card for models that will not fit elsewhere.
Prepaid credits start at $10, minimum top-up $5. Unused credits do not expire.
Switch between hourly on-demand and a reserved month. Reserved capacity is billed upfront and locks the rate for 30 days.
| GPU | Memory | Our rate / hr | Market / hr |
|---|
All prices in USD, excluding applicable taxes. Storage and public IPv4 are billed separately.
List spare capacity, set your own floor price, and get paid for every second a renter is on your hardware. You keep control of what runs and when the node is available.
Per second, from the moment the container starts to the moment it stops. Stopped instances are not billed for compute; attached storage keeps billing until you delete the volume.
Yes. Nodes with 2, 4 and 8 GPUs are listed as single units with NVLink or InfiniBand where the operator provides it. Interconnect bandwidth is shown on every listing.
The job is requeued onto equivalent hardware and you are not charged for the interrupted portion. Checkpoint to a persistent volume so a restart resumes rather than starts over.
Volumes are encrypted at rest and instances are isolated per tenant. ENOSIS does not inspect workload contents. For regulated data, restrict deployment to hosts carrying the compliance attestations you need.
No. On-demand instances can be destroyed at any time. Reserved monthly capacity is the only commitment, and it is optional.
Interruptible instances run at a discount and can be reclaimed with two minutes of notice. They suit checkpointed training and batch inference, not live serving.
Card, memory, how long, and which region. We come back with a concrete quote, usually the same business day.
ENOSIS INC
2647 Gateway Road, Suite 240
Carlsbad, CA 92009
[email protected]