A unified API gateway for accessing multiple large language models and AI services through standardized endpoints.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| gemini-2.0-flash | 181.83 t/s | 1.79s | 5 |
| deepseek-v3-1-terminus | 81.58 t/s | 1.05s | 5 |
| deepseek-ai/DeepSeek-V3-0324 | 38.25 t/s | 1.91s | 25 |
| deepseek-v3.2 | 27.18 t/s | 0.71s | 10 |
| deepseek-v3.2 | 27.18 t/s | 0.71s | 10 |
| deepseek-ai/DeepSeek-V3 | 22.90 t/s | 2.28s | 30 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Dec 30, 03:39 AM | deepseek-v3.2 | 26.40 t/s | 0.59s |
| Dec 30, 03:35 AM | deepseek-v3.2 | 27.96 t/s | 0.82s |
| Dec 30, 03:27 AM | deepseek-v3-1-terminus | 81.58 t/s | 1.05s |
| Dec 30, 03:25 AM | gemini-2.0-flash | 181.83 t/s | 1.79s |
| Aug 29, 10:20 AM | deepseek-ai/DeepSeek-V3-0324 | 37.00 t/s | 2.02s |
| Aug 29, 10:18 AM | deepseek-ai/DeepSeek-V3-0324 | 39.29 t/s | 2.08s |
| Aug 29, 10:16 AM | deepseek-ai/DeepSeek-V3-0324 | 37.20 t/s | 2.09s |
| Aug 29, 10:14 AM | deepseek-ai/DeepSeek-V3-0324 | 38.87 t/s | 1.84s |
| Aug 29, 10:12 AM | deepseek-ai/DeepSeek-V3-0324 | 38.89 t/s | 1.54s |
| Jul 23, 07:42 AM | deepseek-ai/DeepSeek-V3 | 22.07 t/s | 2.49s |