A
Yunchu API
Provides high-performance, cost-effective AI inference APIs with GPT and Grok model support, featuring low latency and high stability.
Provides high-performance, cost-effective AI inference APIs with GPT and Grok model support, featuring low latency and high stability.
| Model | Speed | Latency | Tests |
|---|---|---|---|
| gpt-5.1-codex-max | 189.79 t/s | 5.28s | 5 |
| gpt-5.4 | 79.45 t/s | 2.73s | 5 |
| grok-4.20-beta | 63.19 t/s | 0.79s | 5 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| Mar 28, 12:05 AM | gpt-5.4 | 79.45 t/s | 2.73s |
| Mar 28, 12:04 AM | grok-4.20-beta | 63.19 t/s | 0.79s |
| Mar 28, 12:02 AM |
| gpt-5.1-codex-max |
189.79 t/s |
5.28s |