prod-inference-eu
running
eu-west-1 • NVIDIA H200 SXM • Created 10/5/2026
GPU Utilization
45%
Memory Util.
38%
VRAM Usage
215 / 564 GB
Queue Depth
3
Node Count
1
Monthly Cost
$19,200.00
Network Configuration
VPC CIDR
10.1.0.0/16
Subnet
10.1.1.0/24
Private Endpoint
https://prod-eu.osi-cloud.internal:8443
Scaling Configuration
Total GPUs
4
Total Nodes
1
Deployed Models
| Name | Model | Replicas | GPU Alloc. | Latency (P50/P99) | RPM | Tokens Today | Status |
|---|---|---|---|---|---|---|---|
| deepseek-v4-flash-eu | DeepSeek V4.1 Flash | 2 | 2 | 68ms / 195ms | 2.1K | 31.2M | active |