Amazon Web Services vs Replicate
As of , Amazon Web Services lists the lower on-demand rate on 3 of the 3 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 Replicate $5.04 per GPU-hour on-demand — Amazon Web Services is $1.61 (32%) cheaper.
Cloud GPU rental prices of Amazon Web Services and Replicate, 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.
On-demand, per GPU-hour
| GPU | Amazon Web Services | Replicate | Difference | Cheaper |
|---|---|---|---|---|
| NVIDIA A100 80GB | $3.43 us-east-1 captured Deploy ↗ | $5.04 captured Deploy ↗ | $1.61 (32%) | Amazon Web Services |
| NVIDIA L40S | $1.86 us-east-1 captured Deploy ↗ | $3.51 captured Deploy ↗ | $1.65 (47%) | Amazon Web Services |
| NVIDIA T4 | $0.53 us-east-1 captured Deploy ↗ | $0.81 captured Deploy ↗ | $0.28 (35%) | Amazon Web Services |
GPU by GPU
- NVIDIA A100 80GB: Amazon Web Services $3.43 (us-east-1) vs Replicate $5.04 per GPU-hour on-demand — Amazon Web Services is $1.61 (32%) cheaper.
- NVIDIA L40S: Amazon Web Services $1.86 (us-east-1) vs Replicate $3.51 per GPU-hour on-demand — Amazon Web Services is $1.65 (47%) cheaper.
- NVIDIA T4: Amazon Web Services $0.53 (us-east-1) vs Replicate $0.81 per GPU-hour on-demand — Amazon Web Services is $0.28 (35%) 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: