Amazon Web Services vs Inferless
As of , Amazon Web Services 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: Amazon Web Services $3.43 (us-east-1) vs Inferless $5.36 per GPU-hour on-demand — Amazon Web Services is $1.93 (36%) cheaper.
On-demand, per GPU-hour
| GPU |  Amazon Web Services |  Inferless | Difference | Cheaper |
|---|---|---|---|---|
| NVIDIA A100 80GB median $1.89 · 53 providers · lowest Deep Infra $0.89 | $3.43 us-east-1 captured Deploy ↗ | $5.36 captured Deploy ↗ | $1.93 (36%) | Amazon Web Services |
| NVIDIA T4 median $0.53 · 13 providers · lowest Edgevana $0.15 | $0.53 us-east-1 captured Deploy ↗ | $0.66 captured Deploy ↗ | $0.13 (20%) | Amazon Web Services |
How this is compared
Cloud GPU rental prices of Amazon Web Services 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: Amazon Web Services $3.43 (us-east-1) vs Inferless $5.36 per GPU-hour on-demand — Amazon Web Services is $1.93 (36%) cheaper.
- NVIDIA T4: Amazon Web Services $0.53 (us-east-1) vs Inferless $0.66 per GPU-hour on-demand — Amazon Web Services is $0.13 (20%) 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: