EmpirioLabs vs RunComfy
As of , EmpirioLabs lists the lower on-demand rate on 3 of the 4 GPUs both offer on-demand; RunComfy wins on 1. On the priciest shared card both list on-demand, NVIDIA H200: EmpirioLabs $11.00 vs RunComfy $9.59 per GPU-hour on-demand — RunComfy is $1.41 (13%) cheaper.
On-demand, per GPU-hour
| GPU | Difference | Cheaper | ||
|---|---|---|---|---|
| NVIDIA H200 median $4.54 · 51 providers · lowest Beam $2.09 from | $11.00 captured Deploy ↗ | $9.59 captured Deploy ↗ | $1.41 (13%) | RunComfy |
| NVIDIA H100 80GB (form factor not stated) median $3.80 · 25 providers · lowest Gcore $1.71 | $3.80 captured Deploy ↗ | $7.49 captured Deploy ↗ | $3.69 (49%) | EmpirioLabs |
| NVIDIA A100 80GB median $2.00 · 58 providers · lowest CloudRift $1.05 | $1.70 captured Deploy ↗ | $4.99 captured Deploy ↗ | $3.29 (66%) | EmpirioLabs |
| NVIDIA RTX A6000 median $0.59 · 18 providers · lowest Thunder Compute $0.35 | $0.85 captured Deploy ↗ | $2.50 captured Deploy ↗ | $1.65 (66%) | EmpirioLabs |
How this is compared
Cloud GPU rental prices of EmpirioLabs and RunComfy, 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 H200: EmpirioLabs $11.00 vs RunComfy $9.59 per GPU-hour on-demand — RunComfy is $1.41 (13%) cheaper.
- NVIDIA H100 80GB (form factor not stated): EmpirioLabs $3.80 vs RunComfy $7.49 per GPU-hour on-demand — EmpirioLabs is $3.69 (49%) cheaper.
- NVIDIA A100 80GB: EmpirioLabs $1.70 vs RunComfy $4.99 per GPU-hour on-demand — EmpirioLabs is $3.29 (66%) cheaper.
- NVIDIA RTX A6000: EmpirioLabs $0.85 vs RunComfy $2.50 per GPU-hour on-demand — EmpirioLabs is $1.65 (66%) 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: