A unified API gateway providing access to multiple large language models and AI services through a single interface.
Performance Stats
Avg Speed
67.35t/s
Latency
1.00s
Total Tests
25
Models
5
| Model | Speed | Latency | Tests |
|---|---|---|---|
| gemini-2.0-flash | 163.32 t/s | 0.59s | 5 |
| DeepSeek-V3-Fast | 79.64 t/s | 0.89s | 5 |
| Qwen/Qwen2.5-72B-Instruct | 32.01 t/s | 1.03s | 10 |
| Qwen/Qwen2.5-72B-Instruct | 32.01 t/s | 1.03s | 10 |
| DeepSeek-V3 | 29.76 t/s | 1.44s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Sep 13, 12:54 PM | Qwen/Qwen2.5-72B-Instruct | 32.44 t/s | 1.01s |
| Sep 13, 12:52 PM | Qwen/Qwen2.5-72B-Instruct | 31.58 t/s | 1.05s |
| Sep 13, 12:49 PM | gemini-2.0-flash | 163.32 t/s | 0.59s |
| Sep 13, 12:46 PM | DeepSeek-V3-Fast | 79.64 t/s | 0.89s |
| Sep 13, 12:43 PM | DeepSeek-V3 | 29.76 t/s | 1.44s |