Launch H100 cloud GPUs for Kubernetes, virtual machines, and hosted Comfy workflows with hourly on-demand pricing and no long-term lock-in.
Compare H100 pricing across Kubernetes, virtual machines, and Hosted Comfy. Hourly prices are rounded for display.
Run H100-backed containers, jobs, services, and ingress on Kubernetes.
| Plan | GPU memory | CPU | Memory | Price / hour | Est. / month |
|---|---|---|---|---|---|
| Kubernetes H100 x1 | 80 GB | 8 | 128 GiB | $2.19/hr | $1,598.70 |
| Kubernetes H100 x2 | 160 GB | 16 | 256 GiB | $4.38/hr | $3,197.40 |
| Kubernetes H100 x4 | 320 GB | 32 | 512 GiB | $8.76/hr | $6,394.80 |
| Kubernetes H100 x8 | 640 GB | 64 | 1,024 GiB | $17.52/hr | $12,789.60 |
Launch H100 virtual machines when you need direct guest access.
| Plan | GPU memory | CPU | Memory | Price / hour | Est. / month |
|---|---|---|---|---|---|
| Virtual Machine H100 x1 | 80 GB | 8 | 128 GiB | $2.19/hr | $1,598.70 |
| Virtual Machine H100 x2 | 160 GB | 16 | 256 GiB | $4.38/hr | $3,197.40 |
| Virtual Machine H100 x4 | 320 GB | 32 | 512 GiB | $8.76/hr | $6,394.80 |
| Virtual Machine H100 x8 | 640 GB | 64 | 1,024 GiB | $17.52/hr | $12,789.60 |
Build and run Comfy workflows in a managed browser workspace.
| Plan | GPU memory | CPU | Memory | Price / hour | Est. / month |
|---|---|---|---|---|---|
| Hosted Comfy H100 x1 | 80 GB | 8 | 128 GiB | $2.63/hr | $1,918.44 |
| Hosted Comfy H100 x2 | 160 GB | 16 | 256 GiB | $5.26/hr | $3,836.88 |
| Hosted Comfy H100 x4 | 320 GB | 32 | 512 GiB | $10.51/hr | $7,673.76 |
| Hosted Comfy H100 x8 | 640 GB | 64 | 1,024 GiB | $21.02/hr | $15,347.52 |
H100 capacity for production inference, batch jobs, fine-tuning, and image workloads.
Serve custom model endpoints and OpenAI-compatible text APIs on dedicated H100 capacity.
Run diffusion and Comfy workflows with persistent storage and browser-based access.
Schedule GPU containers and jobs on Kubernetes with clear hourly compute pricing.
Use 80 GB H100 memory per GPU for larger training and adaptation workloads.
Yes. RemoteGPU publishes 1x, 2x, 4x, and 8x H100 plans where capacity is available.
No. Published H100 plans use hourly usage-based pricing unless a separate agreement says otherwise.
Use Kubernetes for container workloads, virtual machines for guest access, Hosted Comfy for Comfy workflows, and Inference API for model endpoints.
