Total requests
1.24M
+18.2%
Monthly spend
$4,820
−6.1%
Avg latency
412ms
−42ms
Error rate
0.42%
−0.08pp
Cost saved via routing
$3,482
+9.1%
Fallback success
99.6%
+0.3pp
Requests over time
last 14 days
Spend by model
Latency by provider
Top models
View all | Model | Requests | Spend |
|---|---|---|
| openai/gpt-4.1 | 184,320 | $1240.55 |
| anthropic/claude-sonnet | 142,880 | $980.10 |
| google/gemini-2.5-pro | 78,110 | $540.32 |
| groq/llama-3.3-70b | 52,640 | $84.20 |
| deepseek/reasoner | 31,040 | $160.88 |
| Time | Model | Tokens | Cost | Latency | Status |
|---|---|---|---|---|---|
| 2026-05-17 09:00:00 | openai/gpt-4.1 | 320 | $0.0032 | 320ms | 200 |
| 2026-05-17 10:07:13 | anthropic/claude-sonnet | 457 | $0.0041 | 411ms | 200 |
| 2026-05-17 11:14:26 | google/gemini-2.5-pro | 594 | $0.0019 | 472ms | 200 |
| 2026-05-17 12:21:39 | meta/llama-4 | 731 | $0.0005 | 713ms | 200 |
| 2026-05-17 13:28:52 | deepseek/reasoner | 868 | $0.0006 | 1004ms | 200 |
| 2026-05-17 14:35:05 | mistral/large-2 | 1,005 | $0.0040 | 515ms | 429 |
| 2026-05-17 15:42:18 | xai/grok-3 | 1,142 | $0.0114 | 626ms | 500 |
| 2026-05-17 16:49:31 | groq/llama-3.3-70b | 1,279 | $0.0009 | 227ms | 200 |