Welcome back, John
Here's what's happening with your models today
Total Models
12
2 added this week
↑ 20%from last month
Active Deployments
8
Across 3 environments
↑ 12%from last month
Total Inferences
1.2M
Last 30 days
↑ 45%from last month
Avg Cold Start
0.8ms
100x faster than containers
↓ 15%from last month
Cost Savings
$4,350
vs GPU infrastructure
↑ 32%from last month
Recent Models
ResNet50-v2
ONNX
Size Reduction-91%
487MB→45MB
Cold Start
0.8ms
Inference
5ms
3 active deployments2 hours ago
BERT-base
TensorFlow
Size Reduction-91%
420MB→38MB
Cold Start
0.9ms
Inference
7ms
2 active deployments5 hours ago
Recent Activity
ResNet50-v2 deployed to edge workers
2 min ago
YOLOv8-nano optimization started
15 min ago
1,234 inferences processed
1 hour ago
New model BERT-base uploaded
3 hours ago
Performance Metrics
Average Cold Start
0.0ms
P95 Inference Time
0.0ms
Model Optimization
0.0%
Resource Usage
Storage Used2.3 GB / 10 GB
API Calls750 / 1000
Compilations45 / ∞
Current Plan
Pro Plan
Ready to optimize more models?
Upload your ONNX, TensorFlow, or PyTorch models and see the magic happen