AI Gateway Performance
Monitor API routing, response times, provider performance, and infrastructure health
124ms
Avg Response Time
-8ms improved
89ms
P95 Response Time
-12ms improved
0.15%
Error Rate
-0.05% improved
99.9%
Uptime
Excellent
Response Time Distribution
Error Rate Monitoring
Detailed Performance Metrics
45ms
P50 Response Time
50% of requests complete within this time
89ms
P95 Response Time
95% of requests complete within this time
156ms
P99 Response Time
99% of requests complete within this time
1,247/min
Throughput
Average requests processed per minute
2.3GB
Memory Usage
Current memory consumption
45%
CPU Utilization
Average CPU usage across instances
API Endpoints Performance
| Method | Endpoint | Description | Status | Avg Response | Success Rate | 24h Calls |
|---|---|---|---|---|---|---|
| POST | /v1/chat/completions | Generate chat completions | 200 | 245ms | 99.2% | 8,247 |
| POST | /v1/embeddings | Create text embeddings | 200 | 123ms | 99.8% | 2,156 |
| POST | /v1/chat/completions | Rate limited request | 429 | 12ms | 0% | 47 |
| GET | /v1/models | List available models | 200 | 89ms | 100% | 892 |
| POST | /v1/images/generations | Generate images from text | 200 | 2.4s | 97.1% | 234 |
| POST | /v1/audio/transcriptions | Transcribe audio to text | 200 | 1.2s | 98.5% | 567 |
| GET | /v1/usage | Get usage statistics | 200 | 67ms | 99.9% | 1,423 |
| POST | /v1/fine-tuning/jobs | Create fine-tuning job | 201 | 456ms | 95.8% | 23 |
| DELETE | /v1/files/{file_id} | Delete uploaded file | 204 | 34ms | 99.6% | 156 |
| PATCH | /v1/assistants/{id} | Update assistant settings | 200 | 178ms | 98.9% | 89 |
| GET | /v1/health | System health check | 200 | 15ms | 100% | 4,892 |
| POST | /v1/moderations | Content moderation | 200 | 78ms | 99.4% | 1,234 |
AWS CloudWatch Performance Monitoring
Advanced performance metrics, alerting, and system health monitoring