Really simple pricing

Connect your cloud and pay nothing! Or connect a card to cover cost of compute. Brev connects to the major clouds to help you find the cheapest GPU. See below for price estimates, or the console for live prices

GPU

GPUHourlySpotProvider
Nvidia L4$0.17$0.05GCP
Nvidia T4$0.40$0.08GCP
Nvidia T4$0.53$0.20AWS
Nvidia K80$0.50$0.05GCP
Nvidia K80$0.90$0.27AWS
Nvidia A10$0.60Lambda-Labs
Nvidia P4$0.65$0.08GCP
Nvidia M60$0.75$0.25AWS
Nvidia A10G$1.01$0.30AWS
Nvidia P100$1.51$0.44GCP
Nvidia V100$2.53$0.75GCP
Nvidia V100$3.06$0.92AWS
Nvidia A100 40GB$1.10Lambda-Labs
Nvidia A100 40GB$3.67$1.21GCP
Nvidia A100 80GB$6.21$2.32GCP
Nvidia H100$1.99Lambda-Labs

CPU

InstancevCPURAMHourlySpot *Provider
2x424$0.04$0.02AWS
2x828$0.08$0.07AWS
4x16416$0.15$0.14AWS
8x32832$0.30$0.29AWS

*The prices are estimates. Check out the console for live prices

Disk

$0.0001314 per GB per hour for the lifetime of an instance

No need to always be on a GPU!

Every Brev instance can be scaled on the fly. No need to stick to a GPU instance if you don't need it. Behind the scenes, we do this by shifting your machine's disk over to a different instance type, briefly restarting it.

Scaling an instance

In the brev console, go to your instance settings and under hardware, you'll see a slider to scale your instance. Or via the CLI run:

brev scale [ Workspace Name or ID... ] --cpu 2x8

(At the moment, this only works for non-SPOT instances. We are working on a fix for SPOT instances so stay tuned 🤙)