Skip to main content

GPU Compute

On-demand GPU workspaces, from one hour to a full cluster

Spin up GPU environments for tuning, training, and experimentation. Root access, a browser terminal, shared filesystems, and up to 96GB of VRAM — billed by the hour.

Compute

From a single GPU to a cluster

Provision exactly what a job needs and tear it down when you're done.

Hourly GPU instances

Launch single-GPU or multi-GPU pods with SSH, Jupyter, and a browser terminal.

Multi-replica clusters

Scale to multiple replicas for distributed training or multi-node serving, managed from one panel.

Web terminal

Drop into a shell from any browser — no SSH key required.

File upload

Upload files straight into your pod from the console.

Auto-expiry protection

Set a duration and instances stop automatically, so you never get a surprise bill.

Up to 96GB VRAM

Professional server GPUs in 1, 2, 4, or 8-GPU configurations.

At a glance

Configurations

GPUs per instance
1 / 2 / 4 / 8
Memory
Up to 96GB VRAM
Billing
Per GPU-hour

Storage

Persistent storage that travels with your work

Keep datasets and model weights close to the GPUs. Storage outlives any single instance and reattaches on demand.

Cloud Drive

Block storage (read-write-once) for a single instance — a durable workspace that survives restarts.

Shared Filesystem

CephFS-backed shared storage (read-write-many) mounted across replicas — ideal for datasets and model weights.

Seamless mounts

Attach storage to any GPU instance; your first drive mounts automatically.

5-day grace period

Suspended storage stays readable for five days, so you can download your data before it is removed.

Get a GPU in seconds

Launch an instance, mount your data, and start building.