A unified API gateway for large language models, offering competitive pricing and stability with support for multiple AI providers.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| MiniMax-M2.5-highspeed | 22.98 t/s | 8.54s | 10 |
| MiniMax-M2.7-highspeed | 7.44 t/s | 3.19s | 25 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Apr 3, 08:16 AM | MiniMax-M2.5-highspeed | 45.95 t/s | 17.08s |
| Apr 3, 08:11 AM | MiniMax-M2.7-highspeed | 37.22 t/s | 15.96s |
| Apr 3, 07:01 AM | MiniMax-M2.7-highspeed | 0.00 t/s | 0.00s |
| Apr 3, 06:40 AM | MiniMax-M2.7-highspeed | 0.00 t/s | 0.00s |
| Apr 3, 06:39 AM | MiniMax-M2.7-highspeed | 0.00 t/s | 0.00s |
| Apr 3, 06:33 AM | MiniMax-M2.7-highspeed | 0.00 t/s | 0.00s |
| Apr 3, 06:33 AM | MiniMax-M2.5-highspeed | 0.00 t/s | 0.00s |