RemoteGPU Pricing
See current pricing for Comfy, Inference API, Kubernetes, Virtual Machine, and Storage.
Hosted workspace
Comfy
Build and run Comfy workflows in the browser.
Hosted Comfy H100 x180 GB8128 GiB$2.63$1,918.44
Hosted Comfy H100 x2160 GB16256 GiB$5.26$3,836.88
Hosted Comfy H100 x4320 GB32512 GiB$10.51$7,673.76
Hosted Comfy H100 x8640 GB641,024 GiB$21.02$15,347.52
Models & endpoints
Inference API
Connect your app to model endpoints.
Qwen/Qwen3.6-27B-FP8$0.30$3.20
Compute Infrastructure
Kubernetes
Deploy containers, jobs, and services with Kubernetes.
Kubernetes H100 x180 GB8128 GiB$2.19$1,598.70
Kubernetes H100 x2160 GB16256 GiB$4.38$3,197.40
Kubernetes H100 x4320 GB32512 GiB$8.76$6,394.80
Kubernetes H100 x8640 GB641,024 GiB$17.52$12,789.60
Compute Infrastructure
Virtual Machine
Launch GPU and CPU virtual machines with direct guest access.
Virtual Machine H100 x180 GB8128 GiB$2.19$1,598.70
Virtual Machine H100 x2160 GB16256 GiB$4.38$3,197.40
Virtual Machine H100 x4320 GB32512 GiB$8.76$6,394.80
Virtual Machine H100 x8640 GB641,024 GiB$17.52$12,789.60
Persistent volumes
Storage
Keep models, files, and outputs across sessions and pods.
Standard Block Storage8 GB$0.001$0.80
Standard Block Storage16 GB$0.002$1.60
Standard Block Storage32 GB$0.004$3.20
Standard Block Storage64 GB$0.009$6.40
Standard Block Storage128 GB$0.018$12.80
Standard Block Storage256 GB$0.035$25.60
Standard Block Storage512 GB$0.07$51.20
Standard Block Storage1 TB$0.14$102.40
Standard Block Storage2 TB$0.281$204.80
Billing notes
- Published rates are billed through Stripe per reserved hour.
- Storage is shown per reserved capacity hour.
- Hourly prices are rounded for display; invoices use exact Stripe metered rates.
- Image inference is billed per compute unit; final usage varies by model, runtime, output size, input images, and request settings.
- Monthly estimates use 730 hours.