Replicate vs Sesterce
As of , Sesterce 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 H100 80GB (form factor not stated): Replicate $5.49 vs Sesterce $2.19 per GPU-hour on-demand — Sesterce is $3.30 (60%) cheaper.
On-demand, per GPU-hour
| GPU |  Replicate |  Sesterce | Difference | Cheaper |
|---|---|---|---|---|
| NVIDIA H100 80GB (form factor not stated) median $3.75 · 28 providers · lowest Gcore $1.72 | $5.49 captured Deploy ↗ | $2.19 from captured Deploy ↗ | $3.30 (60%) | Sesterce |
| NVIDIA A100 80GB median $1.99 · 63 providers · lowest Yotta Labs $0.92 | $5.04 captured Deploy ↗ | $1.49 from captured Deploy ↗ | $3.55 (71%) | Sesterce |
| NVIDIA L40S median $1.42 · 40 providers · lowest CloudRift $0.63 | $3.51 captured Deploy ↗ | $0.97 from captured Deploy ↗ | $2.54 (72%) | Sesterce |
How this is compared
Cloud GPU rental prices of Replicate and Sesterce, 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 H100 80GB (form factor not stated): Replicate $5.49 vs Sesterce $2.19 per GPU-hour on-demand — Sesterce is $3.30 (60%) cheaper.
- NVIDIA A100 80GB: Replicate $5.04 vs Sesterce $1.49 per GPU-hour on-demand — Sesterce is $3.55 (71%) cheaper.
- NVIDIA L40S: Replicate $3.51 vs Sesterce $0.97 per GPU-hour on-demand — Sesterce is $2.54 (72%) 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: