GPU.ai vs Modal
As of , GPU.ai and Modal each list the lower on-demand rate on 4 of the 8 GPUs both offer on-demand. Not counted: 1 more shared GPU, on community capacity or a marketplace floor. On the priciest shared card both list on-demand, NVIDIA B300: GPU.ai $10.11 vs Modal $7.10 per GPU-hour on-demand — Modal is $3.01 (30%) cheaper.
On-demand, per GPU-hour
| GPU | Difference | Cheaper | ||
|---|---|---|---|---|
| NVIDIA B300 median $9.00 · 26 providers · lowest Deep Infra $5.89 | $10.11 from captured Deploy ↗ | $7.10 GPU only captured Deploy ↗ | $3.01 (30%) | Modal |
| NVIDIA B200 median $7.50 · 36 providers · lowest Hostinger $4.50 from | $8.99 from captured Deploy ↗ | $6.25 GPU only captured Deploy ↗ | $2.74 (30%) | Modal |
| NVIDIA H200 median $4.65 · 52 providers · lowest Dataoorts $2.29 | $5.95 from captured Deploy ↗ | $4.54 GPU only captured Deploy ↗ | $1.41 (24%) | Modal |
| NVIDIA H100 SXM median $3.53 · 40 providers · lowest Cudo Compute $1.79 GPU only | $4.94 from captured Deploy ↗ | $3.95 GPU only captured Deploy ↗ | $0.99 (20%) | Modal |
| NVIDIA RTX PRO 6000 Blackwell median $2.20 · 41 providers · lowest Hostinger $0.65 from | $1.90 from captured Deploy ↗ | $3.03 GPU only captured Deploy ↗ | $1.13 (37%) | GPU.ai |
| NVIDIA A100 80GB median $2.04 · 60 providers · lowest Yotta Labs $0.92 | $1.38 from captured Deploy ↗ | $2.50 GPU only captured Deploy ↗ | $1.12 (45%) | GPU.ai |
| NVIDIA L40S median $1.55 · 37 providers · lowest Runcrate $0.55 from | $0.90 from captured Deploy ↗ | $1.95 GPU only captured Deploy ↗ | $1.05 (54%) | GPU.ai |
| NVIDIA L4 median $0.80 · 22 providers · lowest Hikube $0.27 GPU only | $0.78 from captured Deploy ↗ | $0.80 GPU only captured Deploy ↗ | $0.02 (2%) | GPU.ai |
| NVIDIA A100 40GB median $1.98 · 21 providers · lowest Trooper.AI $0.71 from | $0.60 from captured Deploy ↗ | $2.10 GPU only captured Deploy ↗ | — | not the same market |
How this is compared
Cloud GPU rental prices of GPU.ai and Modal, 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 B300: GPU.ai $10.11 vs Modal $7.10 per GPU-hour on-demand — Modal is $3.01 (30%) cheaper.
- NVIDIA B200: GPU.ai $8.99 vs Modal $6.25 per GPU-hour on-demand — Modal is $2.74 (30%) cheaper.
- NVIDIA H200: GPU.ai $5.95 vs Modal $4.54 per GPU-hour on-demand — Modal is $1.41 (24%) cheaper.
- NVIDIA H100 SXM: GPU.ai $4.94 vs Modal $3.95 per GPU-hour on-demand — Modal is $0.99 (20%) cheaper.
- NVIDIA RTX PRO 6000 Blackwell: GPU.ai $1.90 vs Modal $3.03 per GPU-hour on-demand — GPU.ai is $1.13 (37%) cheaper.
- NVIDIA A100 80GB: GPU.ai $1.38 vs Modal $2.50 per GPU-hour on-demand — GPU.ai is $1.12 (45%) cheaper.
- NVIDIA L40S: GPU.ai $0.90 vs Modal $1.95 per GPU-hour on-demand — GPU.ai is $1.05 (54%) cheaper.
- NVIDIA L4: GPU.ai $0.78 vs Modal $0.80 per GPU-hour on-demand — GPU.ai is $0.02 (2%) cheaper.
- NVIDIA A100 40GB: GPU.ai $0.60 (from) vs Modal $2.10 (GPU only) per GPU-hour — not the same market, not counted.
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: