Metriqual Dashboard
Monitor your AI application performance in real-time
+12.5%
2.4M
Total Requests
-8.2%
$4,832
Total Cost
-15.3%
234ms
Avg Latency
-0.04%
0.12%
Error Rate
Request Volume & Cost
Model Usage
GPT-4
$2341(35%)
Claude 3
$1523(25%)
GPT-3.5
$523(20%)
Gemini
$235(10%)
Others
$210(10%)
Recent Requests
1h agoNow
| Timestamp | Model | Endpoint | Latency | Tokens | Cost | Status |
|---|---|---|---|---|---|---|
| 2 min ago | gpt-4 | chat.completions | 342ms | 1,234 | $0.0234 | success |
| 5 min ago | claude-3-opus | messages | 523ms | 2,341 | $0.0452 | success |
| 8 min ago | gpt-4-vision | chat.completions | 1243ms | 3,421 | $0.0821 | success |
| 12 min ago | whisper-1 | audio.transcriptions | 2341ms | 0 | $0.0123 | error |
| 15 min ago | gemini-pro | generateContent | 412ms | 1,523 | $0.0312 | success |