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
59 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 | 2488 ms |
|---|---|
| p95 TTFT | 5176 ms |
| p50 TTFB | 3000 ms |
| Effective throughput | 39 tok/s n=12 |
| Uptime | 98.31% |
Measured model routes
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| google/gemma-4-31b-it | 1212 ms | 1212 ms | 39 tok/s n=2 | 100.00% | — | 2 |
| qwen/qwen3.6-35b-a3b | 1268 ms | 1268 ms | — | 100.00% | — | 2 |
| qwen/qwen3.5-122b-a10b | 1375 ms | 1375 ms | — | 100.00% | — | 2 |
| moonshotai/kimi-k2.7-code | 1589 ms | 1588 ms | 52 tok/s n=1 | 100.00% | — | 3 |
| z-ai/glm-5.2 | 1729 ms | 1729 ms | 30 tok/s n=2 | 100.00% | — | 3 |
| tencent/hunyuan-a13b-instruct | 1745 ms | 1745 ms | — | 100.00% | — | 2 |
| qwen/qwen3.5-9b | 1821 ms | 1820 ms | — | 100.00% | — | 3 |
| google/gemma-4-26b-a4b-it | 1964 ms | 1964 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.1 | 2040 ms | 2039 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v4-pro | 2054 ms | 2054 ms | — | 100.00% | — | 1 |
| z-ai/glm-4.5-air | 2151 ms | 2150 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash | 2209 ms | 2209 ms | 32 tok/s n=1 | 100.00% | — | 1 |
| deepseek/deepseek-v3.2-exp | 2263 ms | 2262 ms | — | 100.00% | — | 2 |
| qwen/qwen3.5-27b | 2488 ms | 2488 ms | — | 100.00% | — | 2 |
| deepseek/deepseek-v3.2 | 2517 ms | 2516 ms | — | 100.00% | 1 unsupported_route |
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 |
| minimax/minimax-m2.5 | 3150 ms | 3150 ms | — | 100.00% | — | 2 |
| qwen/qwen3.6-27b | 3547 ms | 3547 ms | — | 100.00% | — | 1 |
| z-ai/glm-5v-turbo | 3646 ms | 3646 ms | — | 100.00% | — | 6 |
| deepseek/deepseek-v4-flash-0731 | 3879 ms | 3878 ms | 84 tok/s n=1 | 100.00% | — | 3 |
| minimax/minimax-m3 | 3969 ms | 3969 ms | 51 tok/s n=2 | 100.00% | — | 4 |
| z-ai/glm-5 | 4458 ms | 4458 ms | — | 100.00% | — | 5 |
| openai/gpt-oss-120b | 26205 ms | 26204 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 5081 ms | 5081 ms | 24 tok/s n=2 | 50.00% | — | 2 |