GPU marketplace

Lightning AI's GPU marketplace lets you run any type of workload (Studio, Job, Pipeline, Deployment, etc...) on any cloud.

Here's a quick tutorial on using the GPU marketplace with Studios to spin up an on-demand development workspace on any cloud.

Availability types

On-demand

When you start a workload (like a Studio or Job) without reserving machines in advance, it runs on-demand. You pay only for the time you use.

Note: Availability for on-demand depends on supply and demand - popular GPU types may be temporarily sold out.

When starting workloads (like a Studio here) it will run on-demand

Reserved

When workloads need guaranteed capacity or will run continuously, reserve instances in advance. You’ll get dedicated resources at reduced rates.

Contact our team to reserve instances (support@lightning.ai)

Supported providers

You can access machines with over 7 compute providers through Lightning AI.

Cloud agnostic storage

Lightning AI provides cloud agnostic folders that let you store data that can easily move across clouds without ingress/egress fees. This allows you to take advantage of the best available compute without worrying about where your data lives.

Create a "New Folder" and select "Lightning Storage" to create your first cloud-agnostic read/write folder on Lightning AI. This data will be available across any machine.

Create a read/write cloud-agnostic folder using 'Lightning storage'

Unified multi-cloud without the overhead: run workloads across hyperscalers and NeoClouds from a single interface. No rewrites, no re-orchestration, no DevOps burden
Flexible compute choices to match your needs: select GPU resources based on your workload and budget; choose between spot, on-demand, or reserved
Bring your orchestration tools or use ours: use managed Kubernetes, SLURM or bare-metal, no DevOps bottlenecks, no extra setup
No vendor lock-in: Switch providers without rebuilding your stack, Lightning AI ensures portability and adaptability across cloud environments
Always available compute thanks to our expanded provider network: enjoy reliable GPU availability across multiple providers, never be held back by provider shortages or regional limitations

Pricing

Check out our pricing page for the latest prices across clouds, or see them in the Lightning AI platform when requesting a machine.

GPU prices for one instance across providers

Was this page helpful?