Leafcloud vs Replicate
As of , Leafcloud 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 H100 80GB (form factor not stated): Leafcloud $3.58 (ams-1) vs Replicate $5.49 per GPU-hour on-demand — Leafcloud is $1.91 (35%) cheaper.
Cloud GPU rental prices of Leafcloud 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 | Leafcloud | Replicate | Difference | Cheaper |
|---|---|---|---|---|
| NVIDIA H100 80GB (form factor not stated) | $3.58 ams-1 captured Deploy ↗ | $5.49 captured Deploy ↗ | $1.91 (35%) | Leafcloud |
| NVIDIA A100 80GB | $1.83 ams-1 captured Deploy ↗ | $5.04 captured Deploy ↗ | $3.21 (64%) | Leafcloud |
GPU by GPU
- NVIDIA H100 80GB (form factor not stated): Leafcloud $3.58 (ams-1) vs Replicate $5.49 per GPU-hour on-demand — Leafcloud is $1.91 (35%) cheaper.
- NVIDIA A100 80GB: Leafcloud $1.83 (ams-1) vs Replicate $5.04 per GPU-hour on-demand — Leafcloud is $3.21 (64%) 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: