Performance Metrics

Analytics

Monitor performance, costs, and usage across all deployments

Total Requests

+12%

23,950

Avg Latency

-8%

128ms

Error Rate

+2.3%

2.2%

Latency Over Time

Request Volume

Top Performing Deployments

1

llama2-production

5,234 requests

124ms

avg latency

2

bert-api

4,123 requests

98ms

avg latency

3

gpt2-staging

3,456 requests

156ms

avg latency

4

resnet-inference

2,789 requests

89ms

avg latency

5

stable-diffusion

1,567 requests

201ms

avg latency

Performance Insights

🎉

Excellent Performance

Your average latency is 15% below target

💡

Optimization Tip

Consider enabling auto-scaling for peak hours

📊

Traffic Trend

+12% increase in requests this week

Deployment Status Distribution

18

Deployed

75%

4

Deploying

17%

2

Failed

8%