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
24 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 | 3514 ms |
|---|---|
| p95 TTFT | 5150 ms |
| Effective throughput | 80 tok/s n=5 |
| Uptime | 91.67% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| z-ai/glm-5.3-flash | 2523 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.8-preview | 2613 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.3-flashx | 3032 ms | — | 100.00% | — | 4 |
| xiaomi/mimo-v2.6-flash | 3297 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.3 | 3382 ms | 112 tok/s n=2 | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 3514 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4.1-flash | 3619 ms | — | 100.00% | — | 1 |
| stepfun/step-5-preview | 3776 ms | — | 75.00% | — | 4 |
| tencent/hy3 | 4587 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k3 | 5150 ms | 22 tok/s n=1 | 100.00% | — | 2 |
| moonshotai/kimi-k2.7-code | — | 80 tok/s n=1 | — | — | 0 |
| tencent/hy4-preview | — | — | 0.00% | — | 1 |
| z-ai/glm-5.2 | — | 39 tok/s n=1 | — | — | 0 |