# RunPod

Canonical: https://inetgeek.com/gpu/runpod/

Per-GPU cloud billed by the second, with community and secure tiers and no minimum commitment.

## Who it suits

Short experiments and bursty inference — per-second billing and a $0.27 entry card mean an idle hour costs nothing and a small job is genuinely small.

Consider something else if The catalogue mixes community and secure capacity, so the cheapest quoted rate is not always the tier a production workload should sit on.

## What the documentation says

### Storage

- Storage price: Persistent storage from $0.05 per GB per month, in standard and high-performance tiers. ([source](https://www.runpod.io/pricing), read 2026-09-06)

### GPU

- H100 SXM, per GPU-hour: $3.49 per hour for H100 SXM 80GB, single card. The PCIe variant is $2.89 and H100 NVL is $3.19. ([source](https://www.runpod.io/pricing), read 2026-09-06)
- Cheapest GPU, per hour: $0.27 per hour for an RTX A5000 with 24GB. RTX 3090 is $0.50, RTX 4090 $0.74, L40S $1.09. ([source](https://www.runpod.io/pricing), read 2026-09-06)
- Largest GPU offered: 288GB per GPU on B300; B200 at 180GB is $6.79 an hour and H200 at 141GB is $4.59. ([source](https://www.runpod.io/pricing), read 2026-09-06)
- Billing granularity: Per second, with per-hour rates shown for comparison. Clusters can be started with no commitment and scaled to 64 GPUs. ([source](https://www.runpod.io/pricing), read 2026-09-06)

## Compared with

- [RunPod vs CoreWeave](https://inetgeek.com/compare/coreweave-vs-runpod/)
- [RunPod vs Hyperstack](https://inetgeek.com/compare/runpod-vs-hyperstack/)
- [RunPod vs Lambda](https://inetgeek.com/compare/runpod-vs-lambda/)
- [RunPod vs Vast.ai](https://inetgeek.com/compare/vast-ai-vs-runpod/)