SiliconFlow: Models and Prices

Model-as-a-service token platform; reports trillions of tokens a day and 10,000 enterprise customers.

SiliconFlow served 674B tokens of other labs' open-weight models over Nov 2 to Nov 8, 2026 through a large public LLM router, #25 among providers.

Open-weight models

ModelFamilyShare of modelTokens, 7dInput $/MOutput $/MTokens/sUptime 3dContext
DeepSeek V4.1 Flash 1017DeepSeek0.6%355B$0.30$0.5581100.0%1.05M
Hy4 previewHunyuan2.5%89B$0.834$2.5058100.0%1.05M
DeepSeek V4 Flash 0423DeepSeek3.1%69B$0.13$0.285099.8%1.05M
DeepSeek V3.2DeepSeek19.7%39B$0.259$0.801699.7%164K
DeepSeek V4 Pro 0423DeepSeek5.6%28B$1.00$1.5037100.0%1.05M
GLM 5.3 FlashGLM0.2%25B$0.15$0.507599.9%1.05M
GLM 5.3GLM0.6%20B$0.70$2.2058100.0%1.05M
DeepSeek V4.1 FlashDeepSeek<0.1%12B$0.30$1.205299.9%1.05M
GLM 5.2GLM1.4%11B$0.70$2.2076100.0%1.05M
DeepSeek V4 Flash 0731DeepSeek0.3%10B$0.22$0.6656100.0%1.05M
Qwen3.8 2.4T A95BQwen100.0%8B$2.00$6.003699.7%1.05M
DeepSeek V3.2 ExpDeepSeek100.0%2B$0.27$0.411799.6%164K
Qwen3 Coder 30B A3B InstructQwen100.0%2B$0.07$0.282699.8%262K
DeepSeek V4 Pro 0813DeepSeek--$1.32$3.962699.9%1.05M
Gemma 4 31BGemma--$0.75$1.003897.7%262K
Gemma 4 26B A4B Gemma--$0.14$0.405999.9%262K
gpt-oss-120bgpt-oss--$0.15$0.601676.8%131K
Qwen3.6 35B A3BQwen--$0.24$1.802792.1%262K
gpt-oss-20bgpt-oss--$0.04$0.182189.8%131K
Kimi K2.6Kimi--$0.77$3.402399.9%262K
Qwen3.5-9BQwen--$0.10$0.153198.8%262K
DeepSeek V3.1DeepSeek--$0.27$1.001898.3%164K
Kimi K2.7 CodeKimi--$0.859$3.8028100.0%262K
Qwen3.5-35B-A3BQwen--$0.24$1.805898.8%262K
GLM 5GLM--$0.95$2.553598.1%205K
GLM 5.1GLM--$1.19$3.746599.9%205K
Qwen3 32BQwen--$0.14$0.572892.7%131K
Qwen3 30B A3B Instruct 2507Qwen--$0.09$0.302498.3%262K
Kimi K2.5Kimi--$0.50$2.5023100.0%262K
DeepSeek V3 0324DeepSeek--$0.25$1.002089.5%164K
Qwen3.5-27BQwen--$0.25$2.001486.4%262K
Qwen3.6 27BQwen--$0.30$3.20893.0%262K
Qwen3 VL 30B A3B InstructQwen--$0.29$1.00883.0%262K
R1 0528DeepSeek--$0.50$2.181998.8%164K
Qwen3.5-122B-A10BQwen--$0.26$2.083589.4%262K
DeepSeek V3.1 TerminusDeepSeek--$0.27$1.001899.9%164K
GLM 4.5 AirGLM--$0.14$0.8644100.0%131K
Step 3.5 FlashStep--$0.10$0.306999.5%262K
Qwen3 VL 30B A3B ThinkingQwen--$0.29$1.0025100.0%262K
Hunyuan A13B InstructHunyuan--$0.14$0.5728100.0%131K

List prices per million tokens as of November 8, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.

Company

Headquarters
Singapore
Latest financing
Over 2B yuan ($294M) Series B (June 2026), then Series B+ and C rounds; nearly 2.9B yuan raised in 2026.

Sources: Caixin.

Finance your GPUs

Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.

Prefer email? hello@amcompute.com