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
29 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 | 2983 ms |
|---|---|
| p95 TTFT | 9260 ms |
| Effective throughput | 34 tok/s n=6 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| tencent/hy4-preview | 1891 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k3 | 2538 ms | 33 tok/s n=2 | 100.00% | — | 3 |
| tencent/hy3 | 2599 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3 | 2839 ms | 57 tok/s n=1 | 100.00% | — | 2 |
| z-ai/glm-5.3-flash | 2860 ms | — | 100.00% | — | 1 |
| stepfun/step-5-preview | 2983 ms | — | 100.00% | — | 7 |
| z-ai/glm-5.2 | 3077 ms | 34 tok/s n=2 | 100.00% | — | 5 |
| deepseek/deepseek-v4.1-flash | 3854 ms | — | 100.00% | — | 1 |
| xiaomi/mimo-v2.6-flash | 4171 ms | — | 100.00% | — | 1 |
| xiaomi/mimo-v2.6-pro | 5540 ms | — | 100.00% | — | 5 |
| moonshotai/kimi-k2.8-preview | 9260 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | — | — | — | 1 provider_error |
0 |
| moonshotai/kimi-k2.7-code | — | 39 tok/s n=1 | — | — | 0 |