Louez des GPU cloud à l’heure

Prix horaire des GPU cloud

La facturation s’exécute par seconde au tarif horaire indiqué, uniquement pendant que l’instance est en cours. Cliquez sur un GPU pour voir les spécifications complètes, la disponibilité et les options de déploiement en un clic.

How GPU Cloud works

1. Pick a GPU

Choose a card and a runtime storage target from the live catalog.

2. Pick a template

JupyterLab, ComfyUI, a vLLM model server, or a browser web terminal, ready in minutes.

3. Connect

Open the workload in the browser or call it through the authenticated EmpirioLabs connect endpoint.

GPU Cloud: common questions

How is GPU Cloud billed?

Billing is per second at the listed hourly rate, and only while the instance is running. The rate is locked in when you deploy, and stopping or destroying the instance stops the charge.

What can I run on a GPU instance?

One-click templates cover JupyterLab notebooks, ComfyUI, vLLM model serving (bring a Hugging Face model id), and a browser web terminal. You connect through the authenticated EmpirioLabs connect endpoint or call the workload through /v1/gpu/connect/{instance_id}/{path} on the API.

Can I manage GPU Cloud through the API?

Yes. Everything the dashboard does is also available through the API: deploy, stop, and destroy instances under /v1/gpu on api.empiriolabs.ai, and reach the running workload through the connect endpoint. The full reference is in the GPU Cloud docs.

How much storage do instances include?

Runtime storage targets range from 100 to 300 GB with a 150 GB default, bundled into the displayed hourly price.

How do I get started?

Create an EmpirioLabs account, open GPU Cloud in the dashboard, pick a GPU and template, and deploy. Billing is pay-as-you-go credits.