Modal vs Replicate
As of , Modal 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: Modal $2.50 vs Replicate $5.04 per GPU-hour on-demand — Modal is $2.54 (50%) cheaper.
On-demand, per GPU-hour
| GPU |  Modal |  Replicate | Difference | Cheaper |
|---|---|---|---|---|
| NVIDIA A100 80GB median $2.04 · 60 providers · lowest Yotta Labs $0.92 | $2.50 GPU only captured Deploy ↗ | $5.04 captured Deploy ↗ | $2.54 (50%) | Modal |
| NVIDIA L40S median $1.29 · 39 providers · lowest CloudRift $0.69 | $1.95 GPU only captured Deploy ↗ | $3.51 captured Deploy ↗ | $1.56 (44%) | Modal |
| NVIDIA T4 median $0.55 · 17 providers · lowest immers.cloud $0.24 | $0.59 GPU only captured Deploy ↗ | $0.81 captured Deploy ↗ | $0.22 (27%) | Modal |
How this is compared
Cloud GPU rental prices of Modal 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.
GPU by GPU
- NVIDIA A100 80GB: Modal $2.50 vs Replicate $5.04 per GPU-hour on-demand — Modal is $2.54 (50%) cheaper.
- NVIDIA L40S: Modal $1.95 vs Replicate $3.51 per GPU-hour on-demand — Modal is $1.56 (44%) cheaper.
- NVIDIA T4: Modal $0.59 vs Replicate $0.81 per GPU-hour on-demand — Modal is $0.22 (27%) 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: