SiliconFlow
Explore SiliconFlow models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
SiliconFlowsiliconflow
No provider claim
| Provider | SiliconFlow |
|---|---|
| Provider website | https://www.siliconflow.com/ |
| Models | 30 public models |
| Prepaid routes | 30 |
| BYOK routes | 29 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | No provider-ZDR claim is tracked here. SiliconFlow's privacy policy source is linked for retention and interaction-data terms. Policy source |
Measured performance
50 samplesContinuously sampled across SiliconFlow's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 1853 ms |
|---|---|
| Effective throughput | 40 tok/s n=13 |
| Uptime | 100.00% |
| Model | p50 TTFT | p50 TTFB | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|---|
| moonshotai/kimi-k2.7-code | 1203 ms | 1202 ms | 59 tok/s n=1 | 100.00% | — | 2 |
| moonshotai/kimi-k2.5 | 1289 ms | 1289 ms | — | 100.00% | — | 4 |
| tencent/hunyuan-a13b-instruct | 1406 ms | 1406 ms | — | 100.00% | — | 5 |
| google/gemma-4-12b-it | 1478 ms | 1477 ms | — | 100.00% | — | 2 |
| z-ai/glm-5.2 | 1623 ms | 1623 ms | 76 tok/s n=2 | 100.00% | — | 2 |
| deepseek/deepseek-v4-flash | 1768 ms | 1768 ms | 89 tok/s n=2 | 100.00% | — | 3 |
| minimax/minimax-m2.5 | 1768 ms | 1768 ms | — | 100.00% | — | 2 |
| openai/gpt-oss-20b | 1793 ms | 1793 ms | — | 100.00% | — | 2 |
| qwen/qwen3.6-35b-a3b | 1853 ms | 1853 ms | — | 100.00% | — | 3 |
| deepseek/deepseek-v3.1-terminus | 1869 ms | 1869 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-pro-0423 | 2036 ms | 2036 ms | 40 tok/s n=2 | 100.00% | — | 1 |
| qwen/qwen3.5-122b-a10b | 2056 ms | 2056 ms | — | 100.00% | — | 3 |
| tencent/hy3 | 2450 ms | 2450 ms | — | 100.00% | — | 3 |
| z-ai/glm-5.1 | 2481 ms | 2481 ms | — | 100.00% | — | 1 |
| moonshotai/kimi-k3 | 3362 ms | 3362 ms | 17 tok/s n=2 | 100.00% | — | 1 |
| deepseek/deepseek-v3.2-exp | 4470 ms | 4470 ms | — | 100.00% | — | 1 |
| google/gemma-4-26b-a4b-it | 4528 ms | 4528 ms | — | 100.00% | — | 1 |
| openai/gpt-oss-120b | 4541 ms | 4541 ms | — | 100.00% | — | 5 |
| z-ai/glm-5 | 4767 ms | 4767 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v4-flash-0731 | 4837 ms | 4837 ms | — | 100.00% | — | 1 |
| google/gemma-4-31b-it | 4927 ms | 4927 ms | 27 tok/s n=2 | 100.00% | — | 1 |
| minimax/minimax-m3 | 5078 ms | 5078 ms | 40 tok/s n=2 | 100.00% | — | 2 |
| qwen/qwen3.5-27b | 27633 ms | 27633 ms | — | 100.00% | — | 1 |
| deepseek/deepseek-v3.2 | — | — | — | 100.00% | — | 2 |
SiliconFlow performance history · Full provider & model leaderboard.
Models served by SiliconFlow.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
deepseek/deepseek-v3.1-terminusDeepSeek: DeepSeek V3.1 Terminus |
— | 163,840 | 2 | $0.28485/1M | $1.055/1M | prepaid BYOK |
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2 |
IQ 103#64 | 163,840 | 2 | $0.28485/1M | $0.4431/1M | prepaid BYOK |
deepseek/deepseek-v3.2-expDeepSeek: DeepSeek V3.2 Exp |
— | 163,840 | 2 | $0.28485/1M | $0.43255/1M | prepaid BYOK |
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash 0423 |
IQ 113#41 | 1,048,576 | 2 | $0.13715/1M | $0.2954/1M | prepaid BYOK |
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,048,576 | 2 | $0.13715/1M | $0.2954/1M | prepaid BYOK |
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro |
IQ 117#31 | 1,048,576 | 2 | $1.58421/1M | $3.307425/1M | prepaid BYOK |
deepseek/deepseek-v4-pro-0423DeepSeek V4 Pro 0423 |
— | 1,048,576 | 1 | $1.58421/1M | $3.307425/1M | prepaid |
google/gemma-4-12b-itgoogle/gemma-4-12B-it |
IQ 98#81 | 0 | 2 | $0.1055/1M | $0.3165/1M | prepaid BYOK |
google/gemma-4-26b-a4b-itGoogle: Gemma 4 26B A4B |
IQ 96#89 | 262,144 | 2 | $0.1266/1M | $0.422/1M | prepaid BYOK |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#73 | 262,144 | 2 | $0.13715/1M | $0.422/1M | prepaid BYOK |
minimax/minimax-m2.5MiniMax: MiniMax M2.5 |
IQ 105#63 | 204,800 | 2 | $0.3165/1M | $1.266/1M | prepaid BYOK |
minimax/minimax-m3MiniMax: MiniMax M3 |
IQ 114#39 | 1,048,576 | 2 | $0.3165/1M | $1.266/1M | prepaid BYOK |
moonshotai/kimi-k2.5MoonshotAI: Kimi K2.5 |
IQ 111#46 | 262,144 | 2 | $0.47475/1M | $2.37375/1M | prepaid BYOK |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 119#23 | 262,144 | 2 | $0.81235/1M | $3.587/1M | prepaid BYOK |
moonshotai/kimi-k2.7-codeMoonshotAI: Kimi K2.7 Code |
IQ 118#28 | 262,144 | 2 | $0.906414/1M | $4.009/1M | prepaid BYOK |
moonshotai/kimi-k3MoonshotAI: Kimi K3 |
IQ 123#16 | 1,048,576 | 2 | $3.165/1M | $15.825/1M | prepaid BYOK |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#61 | 131,072 | 2 | $0.05275/1M | $0.47475/1M | prepaid BYOK |
openai/gpt-oss-20bOpenAI: gpt-oss-20b |
IQ 100#77 | 131,072 | 2 | $0.0422/1M | $0.1899/1M | prepaid BYOK |
qwen/qwen3.5-122b-a10bQwen: Qwen3.5-122B-A10B |
— | 262,144 | 2 | $0.2743/1M | $2.1944/1M | prepaid BYOK |
qwen/qwen3.5-27bQwen: Qwen3.5-27B |
— | 262,144 | 2 | $0.26375/1M | $2.11/1M | prepaid BYOK |
qwen/qwen3.5-9bQwen: Qwen3.5-9B |
IQ 93#99 | 262,144 | 2 | $0.1055/1M | $0.15825/1M | prepaid BYOK |
qwen/qwen3.6-27bQwen: Qwen3.6 27B |
IQ 111#47 | 262,144 | 2 | $0.3165/1M | $3.376/1M | prepaid BYOK |
qwen/qwen3.6-35b-a3bQwen: Qwen3.6 35B A3B |
IQ 100#78 | 262,144 | 2 | $0.211/1M | $1.688/1M | prepaid BYOK |
tencent/hunyuan-a13b-instructTencent: Hunyuan A13B Instruct |
— | 131,072 | 2 | $0.1477/1M | $0.60135/1M | prepaid BYOK |
tencent/hy3Tencent: Hy3 |
IQ 103#67 | 262,144 | 2 | $0.13926/1M | $0.55704/1M | prepaid BYOK |
z-ai/glm-4.5-airZ.ai: GLM 4.5 Air |
— | 131,072 | 2 | $0.1477/1M | $0.9073/1M | prepaid BYOK |
z-ai/glm-5Z.ai: GLM 5 |
IQ 105#60 | 204,800 | 2 | $1.00225/1M | $2.69025/1M | prepaid BYOK |
z-ai/glm-5.1Z.ai: GLM 5.1 |
IQ 114#38 | 204,800 | 2 | $1.25545/1M | $3.9457/1M | prepaid BYOK |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#19 | 1,048,576 | 2 | $1.37361/1M | $4.31706/1M | prepaid BYOK |
z-ai/glm-5v-turboZ.ai: GLM 5V Turbo |
— | 202,752 | 2 | $1.266/1M | $4.22/1M | prepaid BYOK |
Questions
Does SiliconFlow have zero data retention?
TrustedRouter does not currently mark SiliconFlow as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is SiliconFlow end-to-end encrypted?
TrustedRouter does not currently mark SiliconFlow as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which SiliconFlow models are available through TrustedRouter?
This page currently lists 30 public SiliconFlow models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.