A unified API gateway for large language models, offering access to multiple providers through standardized endpoints.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| gemini-2.5-flash-preview-05-20-max | 224.58 t/s | 7.44s | 10 |
| gemini-2.5-flash-fastmax | 196.98 t/s | 10.93s | 5 |
| gemini-2.5-pro-preview-06-05-max | 106.92 t/s | 13.33s | 20 |
| gemini-2.5-pro-fastmax | 89.41 t/s | 23.79s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Jun 25, 04:41 PM | gemini-2.5-flash-fastmax | 196.98 t/s | 10.93s |
| Jun 25, 04:11 PM | gemini-2.5-pro-fastmax | 89.41 t/s | 23.79s |
| Jun 13, 10:06 PM | gemini-2.5-pro-preview-06-05-max | 104.31 t/s | 16.05s |
| Jun 13, 10:04 PM | gemini-2.5-pro-preview-06-05-max | 107.49 t/s | 9.51s |
| Jun 13, 07:46 PM | gemini-2.5-flash-preview-05-20-max | 263.73 t/s | 7.40s |
| Jun 13, 06:58 PM | gemini-2.5-flash-preview-05-20-max | 185.43 t/s | 7.48s |
| Jun 13, 06:53 PM | gemini-2.5-pro-preview-06-05-max | 110.10 t/s | 13.97s |
| Jun 13, 06:36 PM | gemini-2.5-pro-preview-06-05-max | 105.80 t/s | 13.79s |