OpenAI compatible API · Attested · Public status
SiliconFlow performance
Measured TTFT, TTFB, effective throughput, uptime, and sampled model routes for SiliconFlow.
Onebase URL to migrate
100sof models and routes
0prompt or output logs. Always.
siliconflow
52 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 | 3291 ms |
|---|---|
| p95 TTFT | 9705 ms |
| p50 TTFB | 3370 ms |
| Effective throughput | 35 tok/s n=10 |
| Uptime | 98.08% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| z-ai/glm-5.2 | 1308 ms | 1308 ms | 29 tok/s n=1 | 100.00% | — | 2 |
| qwen/qwen3.5-122b-a10b | 1375 ms | 1375 ms | — | 100.00% | — | 2 |
| qwen/qwen3.6-27b | 1745 ms | 1745 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.1 | 1768 ms | 1768 ms | — | 100.00% | — | 4 |
| deepseek/deepseek-v4-pro | 1814 ms | 1814 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | 1870 ms | 1870 ms | 40 tok/s n=1 | 100.00% | — | 1 |
| minimax/minimax-m3 | 1883 ms | 1883 ms | 40 tok/s n=1 | 100.00% | — | 1 |
| google/gemma-4-26b-a4b-it | 1964 ms | 1964 ms | — | 100.00% | — | 4 |
| z-ai/glm-4.5-air | 2151 ms | 2150 ms | — | 100.00% | — | 1 |
| qwen/qwen3.5-27b | 2488 ms | 2488 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.2 | 2517 ms | 2516 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v3.1-terminus | 2596 ms | 2595 ms | — | 100.00% | — | 1 |
| tencent/hy3 | 3000 ms | 3000 ms | 41 tok/s n=1 | 100.00% | — | 1 |
| qwen/qwen3.6-35b-a3b | 3291 ms | 3291 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v3.2-exp | 3370 ms | 3370 ms | — | 100.00% | — | 3 |
| minimax/minimax-m2.5 | 3454 ms | 3454 ms | — | 100.00% | — | 3 |
| moonshotai/kimi-k2.7-code | 3547 ms | 3547 ms | 35 tok/s n=2 | 100.00% | — | 1 |
| tencent/hunyuan-a13b-instruct | 3682 ms | 3682 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-flash-0731 | 3879 ms | 3878 ms | 84 tok/s n=1 | 100.00% | — | 1 |
| z-ai/glm-5v-turbo | 4010 ms | 4010 ms | — | 100.00% | — | 6 |
| z-ai/glm-5 | 4135 ms | 4135 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-flash | 5820 ms | 5819 ms | 32 tok/s n=1 | 100.00% | — | 1 |
| openai/gpt-oss-120b | 26205 ms | 26204 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 4012 ms | 4012 ms | 24 tok/s n=2 | 75.00% | — | 4 |