OpenAI compatible API · Attested · Public status
Tencent Cloud TokenHub performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for Tencent Cloud TokenHub on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
Tencent Cloud TokenHubtencent
31 samples
Continuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 2714 ms |
|---|---|
| p95 TTFT | 10832 ms |
| Effective throughput | 38 tok/s n=5 |
| Uptime | 96.77% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4.1-flash | 1806 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 2264 ms | 72 tok/s n=1 | 100.00% | — | 3 |
| xiaomi/mimo-v2.6-flash | 2323 ms | — | 66.67% | — | 3 |
| z-ai/glm-5.3-flash | 2377 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2.7-code-highspeed | 2415 ms | — | 100.00% | — | 3 |
| tencent/hy3 | 2677 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.8-preview | 2714 ms | — | 100.00% | — | 6 |
| moonshotai/kimi-k3 | 3244 ms | 14 tok/s n=1 | 100.00% | — | 1 |
| z-ai/glm-5.2 | 3677 ms | 38 tok/s n=2 | 100.00% | — | 5 |
| stepfun/step-5-preview | 3777 ms | — | 100.00% | — | 1 |
| xiaomi/mimo-v2.6-pro | 4012 ms | — | 100.00% | — | 4 |
| z-ai/glm-5.3 | — | 71 tok/s n=1 | — | — | 0 |