GPU Cloud
H100 (Infiniband)
H100 Konfiguration mit Infiniband (3.2Tbit/s): 2 Intel Xeon 8480+ / 2TB RAM / 8x3.84TB NVMe / 8x Nvidia H100, IB 3.2Tbit/s, 2x100Gbit/s Ethernet
| H100 Preis pro GPU | 1 Monat (rollierend) | 6 Monate (fest reserviert) | 12 Monate (fest reserviert) | 36 Monate (fest reserviert) |
|---|
| Mehr als 512 GPUs | €3.30/Stunde | €3.15/Stunde | €3.05/Stunde | €2.90/Stunde |
| 128 bis 512 GPUs | €3.60/Stunde | €3.30/Stunde | €3.25/Stunde | €3.10/Stunde |
| 32 bis 128 GPUs | €3.70/Stunde | €3.50/Stunde | €3.40/Stunde | €3.25/Stunde |
| Weniger als 32 GPUs | €3.75/Stunde | €3.60/Stunde | €3.50/Stunde | €3.35/Stunde |
Preise zzgl. MwSt.
A100 (Infiniband)
A100 Konfiguration mit Infiniband 800Gbit/s: 2 Intel Xeon 8468 / 2 TB RAM / 8x3.84 TB NVMe / 8x Nvidia A100 / 800Gbit/s Infiniband
| H100 Preis pro GPU | 1 Monat (rollierend) | 6 Monate (fest reserviert) | 12 Monate (fest reserviert) | 36 Monate (fest reserviert) |
|---|
| 128 bis 512 GPUs | €1.98/Stunde | €1.60/Stunde | €1.58/Stunde | €1.30/Stunde |
| 32 bis 128 GPUs | €2.03/Stunde | €1.70/Stunde | €1.65/Stunde | €1.36/Stunde |
| Weniger als 32 GPUs | €2.06/Stunde | €1.74/Stunde | €1.70/Stunde | €1.40/Stunde |
Preise zzgl. MwSt.
A100
A100 80GB Konfiguration ohne Infiniband: 2 Intel Xeon 8468 / 2 TB RAM / 8x3.84 TB NVMe / 8x Nvidia A100, 2x100Gbit/s Ethernet
| H100 Preis pro GPU | 1 Monat (rollierend) | 6 Monate (fest reserviert) | 12 Monate (fest reserviert) | 36 Monate (fest reserviert) |
|---|
| 128 bis 512 GPUs | €1.92/Stunde | €1.54/Stunde | €1.52/Stunde | €1.25/Stunde |
| 32 bis 128 GPUs | €1.97/Stunde | €1.64/Stunde | €1.59/Stunde | €1.31/Stunde |
| Weniger als 32 GPUs | €2.00/Stunde | €1.70/Stunde | €1.64/Stunde | €1.35/Stunde |
Preise zzgl. MwSt.
L40s
L40s Konfiguration: 2x Intel Xeon 8468 / 2TB RAM / 4x7,68TB NVMe RI SSD + 2x960SSD OS / 8x Nvidia L40S / 2x10Gbit/s Ethernet
| L40s | 1 Monat (rollierend) | 6 Monate (fest reserviert) | 12 Monate (fest reserviert) | 36 Monate (fest reserviert) |
|---|
| Mehr als 512 GPUs | €1.64/Stunde | €1.50/Stunde | €1.41/Stunde | €1.28/Stunde |
| 128 bis 512 GPUs | €1.91/Stunde | €1.64/Stunde | €1.59/Stunde | €1.46/Stunde |
| 32 bis 128 GPUs | €2.00/Stunde | €1.82/Stunde | €1.73/Stunde | €1.59/Stunde |
| Weniger als 32 GPUs | €2.05/Stunde | €1.91/Stunde | €1.82/Stunde | €1.69/Stunde |
Preise zzgl. MwSt.
H200
H200 80GB with Infiniband 3.2Tbit/s
2 Intel Xeon 8480+ / 2TB RAM / 2x 960GB SSD + 8x3.84 TB NVMe / 8x Nvidia H200, IB 3.2 Tbit/s, 2x100Gbit/s Ethernet
| Price per GPU | 1 month Rolling | 6 months Reserved | 12 months Reserved | 36 months Reserved |
|---|
| Greater than 512 GPUs | €3.40/hour | €3.25/hour | €3.15/hour | €3.00/hour |
| 128 to 512 GPUs | €3.70/hour | €3.40/hour | €3.35/hour | €3.20/hour |
| 32 to 128 GPUs | €3.80/hour | €3.60/hour | €3.50/hour | €3.35/hour |
| Less than 32 GPUs | €3.85/hour | €3.70/hour | €3.60/hour | €3.45/hour |
H200 GPUs available upon request. Contact us for availability and pricing.
Preise zzgl. MwSt.
GB200
Available upon request. Contact us for availability and pricing.
Everywhere Inference
Billing is determined by the exact compute time you use, measured down to the minute. Benefit
from effortless autoscaling, fast cold starts, and a wide range of GPU options, along with secure
deployments and protected endpoints - all while keeping costs low.
Preise zzgl. MwSt.
For third-party cloud and on-premise deployments please get in touch with our sales team.