A unified LLM API gateway providing access to multiple AI models through standardized endpoints.
Performance Stats
Avg Speed
76.56t/s
Latency
1.03s
Total Tests
40
Models
2
| Model | Speed | Latency | Tests |
|---|---|---|---|
| gemini-2.0-flash | 171.32 t/s | 1.85s | 5 |
| deepseek | 63.03 t/s | 0.92s | 35 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Jan 3, 12:40 AM | deepseek | 17.23 t/s | 0.91s |
| Jan 3, 12:36 AM | deepseek | 16.14 t/s | 0.94s |
| Jan 1, 11:15 PM | deepseek | 89.05 t/s | 1.03s |
| Jan 1, 07:53 AM | deepseek | 19.15 t/s | 0.88s |
| Jan 1, 07:37 AM | deepseek | 124.43 t/s | 0.90s |
| Jan 1, 05:48 AM | gemini-2.0-flash | 171.32 t/s | 1.85s |
| Jan 1, 04:15 AM | deepseek | 88.33 t/s | 0.81s |
| Jan 1, 03:58 AM | deepseek | 86.87 t/s | 0.96s |