OpenAI compatible API · Attested · Public status
SiliconFlow performance
Review measured TTFT, effective throughput, uptime, and sampled model routes for SiliconFlow on TrustedRouter using metadata-only production probes.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
SiliconFlowsiliconflow
27 samplesContinuously sampled provider performance. TrustedRouter reports unsupported route and probe-configuration rows separately from provider downtime. Prompt and output content is not stored.
| p50 TTFT | 1714 ms |
|---|---|
| p95 TTFT | 3394 ms |
| Effective throughput | 95 tok/s n=9 |
| Uptime | 100.00% |
Measured model routes
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| z-ai/glm-5.1 | 981 ms | — | 100.00% | — | 2 |
| qwen/qwen3.6-35b-a3b | 1149 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.6 | 1192 ms | 23 tok/s n=1 | 100.00% | — | 1 |
| qwen/qwen3.5-122b-a10b | 1323 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4.1-flash | 1390 ms | — | 100.00% | — | 2 |
| google/gemma-4-26b-a4b-it | 1457 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.7-code | 1494 ms | 24 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro-0423 | 1659 ms | 63 tok/s n=1 | 100.00% | — | 2 |
| tencent/hunyuan-a13b-instruct | 1712 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-20b | 1714 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.3-flash | 1750 ms | — | 100.00% | — | 2 |
| qwen/qwen3.5-9b | 1775 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-vision-exp | 1828 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k2.5 | 1891 ms | — | 100.00% | — | 2 |
| qwen/qwen3.8-2.4t-a95b | 2116 ms | — | 100.00% | — | 1 |
| tencent/hy3 | 2245 ms | — | 100.00% | — | 1 |
| z-ai/glm-5.2 | 2512 ms | 97 tok/s n=1 | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 3099 ms | 19 tok/s n=1 | 100.00% | — | 3 |
| openai/gpt-oss-120b | 3547 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | — | 95 tok/s n=1 | — | — | 0 |
| minimax/minimax-m3 | — | 110 tok/s n=2 | — | — | 0 |
| z-ai/glm-5.3 | — | 108 tok/s n=1 | — | — | 0 |