Google Cloud vs Inferless
As of , Google Cloud lists the lower on-demand rate on 2 of the 2 GPUs both offer on-demand. On the priciest shared card both list on-demand, NVIDIA A100 80GB: Google Cloud $3.93 (us-central1) vs Inferless $5.36 per GPU-hour on-demand — Google Cloud is $1.43 (27%) cheaper.
On-demand, per GPU-hour
| GPU |  Google Cloud |  Inferless | Difference | Cheaper |
|---|---|---|---|---|
| NVIDIA A100 80GB median $1.89 · 53 providers · lowest Deep Infra $0.89 | $3.93 us-central1 · GPU only captured Deploy ↗ | $5.36 captured Deploy ↗ | $1.43 (27%) | Google Cloud |
| NVIDIA T4 median $0.53 · 13 providers · lowest Edgevana $0.15 | $0.35 us-east5 · GPU only captured Deploy ↗ | $0.66 captured Deploy ↗ | $0.31 (47%) | Google Cloud |
Spot / interruptible, per GPU-hour
| GPU | Google Cloud | Inferless |
|---|---|---|
| NVIDIA A100 80GB | $0.40 captured | — |
How this is compared
Cloud GPU rental prices of Google Cloud and Inferless, compared per GPU-hour on the GPUs both list. Where a provider has several tiers or regions, its cheapest on-demand rate is used and labelled. Community capacity (RunPod Community Cloud) and marketplace floors are shown only where a provider has nothing else, and never decide which is cheaper.
GPU by GPU
- NVIDIA A100 80GB: Google Cloud $3.93 (us-central1) vs Inferless $5.36 per GPU-hour on-demand — Google Cloud is $1.43 (27%) cheaper.
- NVIDIA T4: Google Cloud $0.35 (us-east5) vs Inferless $0.66 per GPU-hour on-demand — Google Cloud is $0.31 (47%) cheaper.
Not compared: GPUs only one of the two lists, reserved/committed tiers, and anything either provider prices only on request. See each provider's page for its full list.
Data updated: