OpenAI compatible API · Attested · Public status
SiliconFlow performance
Review measured TTFT, TTFB, 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
56 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 | 2028 ms |
|---|---|
| p95 TTFT | 8775 ms |
| p50 TTFB | 2453 ms |
| Effective throughput | 50 tok/s n=12 |
| Uptime | 98.21% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| moonshotai/kimi-k2.7-code | 1091 ms | 1091 ms | 43 tok/s n=1 | 100.00% | — | 3 |
| deepseek/deepseek-v4-flash-0731 | 1533 ms | 1533 ms | 73 tok/s n=2 | 100.00% | — | 2 |
| z-ai/glm-4.5-air | 1535 ms | 1535 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.5 | 1637 ms | 1637 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-9b | 1677 ms | 1676 ms | — | 100.00% | — | 7 |
| z-ai/glm-5.2 | 1820 ms | 1820 ms | 31 tok/s n=1 | 100.00% | — | 3 |
| google/gemma-4-31b-it | 1847 ms | 1847 ms | 12 tok/s n=1 | 100.00% | — | 2 |
| openai/gpt-oss-20b | 1874 ms | 1873 ms | — | 100.00% | — | 2 |
| tencent/hy3 | 2028 ms | 2028 ms | 75 tok/s n=2 | 100.00% | — | 3 |
| qwen/qwen3.5-122b-a10b | 2065 ms | 2065 ms | — | 100.00% | — | 3 |
| qwen/qwen3.6-35b-a3b | 2210 ms | 2210 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-flash | 2236 ms | 2236 ms | 47 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v3.2 | 2453 ms | 2453 ms | — | 100.00% | — | 2 |
| z-ai/glm-5v-turbo | 2666 ms | 2666 ms | — | 100.00% | — | 1 |
| tencent/hunyuan-a13b-instruct | 2977 ms | 2977 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.1 | 3191 ms | 3190 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-120b | 3285 ms | 3285 ms | 15 tok/s n=1 | 100.00% | — | 2 |
| moonshotai/kimi-k3 | 3343 ms | 3343 ms | 29 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro | 3870 ms | 3870 ms | 54 tok/s n=1 | 100.00% | — | 4 |
| deepseek/deepseek-v3.1-terminus | 4410 ms | 4410 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v3.2-exp | 4662 ms | 4662 ms | — | 100.00% | — | 5 |
| qwen/qwen3.5-27b | 1675 ms | 1674 ms | — | 66.67% | — | 3 |
| minimax/minimax-m3 | — | — | 172 tok/s n=1 | — | — | 0 |