A unified LLM API gateway providing access to multiple AI models through standardized endpoints.
Performance Stats
Avg Speed
89.32t/s
Latency
2.20s
Total Tests
60
Models
4
| Model | Speed | Latency | Tests |
|---|---|---|---|
| gemini-3-flash-preview | 129.69 t/s | 6.75s | 5 |
| auto-translator | 94.28 t/s | 1.96s | 45 |
| GLM-4-FlashX | 64.39 t/s | 0.47s | 5 |
| deepseek-chat | 29.23 t/s | 1.52s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Feb 12, 10:29 AM | auto-translator | 110.88 t/s | 0.74s |
| Feb 2, 03:50 AM | auto-translator | 88.65 t/s | 0.63s |
| Feb 2, 03:45 AM | gemini-3-flash-preview | 129.69 t/s | 6.75s |
| Feb 2, 03:41 AM | auto-translator | 92.51 t/s | 0.57s |
| Feb 2, 03:37 AM | GLM-4-FlashX | 64.39 t/s | 0.47s |
| Jan 29, 11:19 PM | auto-translator | 107.83 t/s | 0.53s |
| Jan 29, 11:10 PM | auto-translator | 101.71 t/s | 0.62s |
| Jan 29, 10:54 PM | auto-translator | 76.29 t/s | 0.64s |
| Jan 29, 10:52 PM | auto-translator | 114.03 t/s | 10.91s |
| Jan 28, 01:38 AM | auto-translator | 72.28 t/s | 0.63s |