A unified AI access and governance platform compatible with OpenAI API specifications, offering quota management, auditing, and real-time monitoring.
Categories
晴辰云 offers 3 LLM API models.
Speed benchmark average: 94 tok/s.
gpt.qt.cool| Time | Model | Speed | Latency |
|---|---|---|---|
| Apr 2, 08:19 AM | gpt-5.2-codex | 65.36 tok/s | 1.76s |
| Mar 19, 07:08 AM | gpt-5.1-codex-mini | 163.63 tok/s | 1.20s |
| Mar 19, 05:55 AM | gpt-5.1-codex-mini | 142.78 tok/s | 1.84s |
| Mar 18, 10:38 AM | gpt-5.4 | 60.78 tok/s | 5.82s |
| Mar 18, 10:36 AM | gpt-5.2-codex | 52.24 tok/s | 1.45s |
| Mar 18, 09:11 AM | gpt-5.2-codex | 24.34 tok/s | 9.32s |
| Mar 17, 09:33 AM | gpt-5.1-codex-mini | 94.24 tok/s | 2.52s |