Skip to main content

SiliconFlow

CNInference host

SiliconFlow runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.

Other region:SiliconFlowGlobal

PricingDocscontact@siliconflow.com
Visit siliconflow.cn
Models59
Cheapest for
15 models
Serves
5 model types
Visits in September 20261.5M−34.9%Unique visitors 494K
  1. Apr
  2. May
  3. Jun
  4. Jul
  5. Aug
  6. Sep
Models by type

Models on SiliconFlow

ModelInputOutputvs officialContext
GLM-5.3$0.833/1M$3.89/1M
from $1.10 at NanoGPT
-12%—
DeepSeek V4.1 Flash$0.278/1M$1.11/1M
from $0.03 at UnoRouter
+3604%—
Qwen3.8 27B$0.25/1M$2/1M
from $0.50 at EmpirioLabs AI
-33%—
GLM-5.2$0.833/1M$3.89/1M
from $1.80 at Deep Infra
-12%—
DeepSeek V4 Flash$0.139/1M$0.278/1M
from $0.17 at Opper
+63%—
DeepSeek V4 Pro$1.67/1M$3.33/1M
from $0.418 at OpenRouter
+698%—
Z Image Turbo—$0.014/img
from $0.005 at Atlas Cloud
+178%—
Qwen Image Edit—$0.042/img
from $0.03 at Replicate
+39%—
Z Image—$0.042/img——
Qwen3.5 9B$0.208/1M$1.67/1M
from $0.13 at EmpirioLabs AI
+1182%—
Qwen3.6 35B-A3B$0.222/1M$1.78/1M
from $0.95 at Deep Infra
-21%—
Kimi K2.6$0.903/1M$3.75/1M
from $2.40 at APIYI
±0%—
GLM-5.1$0.833/1M$3.89/1M
from $1.44 at APIMart
-12%—
Qwen3-VL-8B-InstructCheapest$0.069/1M$0.278/1M——
Kimi K2.7 Code HighSpeed$0.903/1M$3.75/1M
from $2.76 at Kenari
±0%—
Qwen3-VL-8B-ThinkingCheapest$0.069/1M$0.694/1M——
Qwen3-Omni-30B-A3B-CaptionerOnly here$0.097/1M$0.389/1M——
Qwen 3 Embedding 4BCheapest—$0.019/1M——
Qwen3.6 27B$0.25/1M$2/1M-44%—
LongCat-2.0$0.694/1M$2.78/1M
from $1.20 at Atlas Cloud
+131%—
Qwen3 14B$0.069/1M$0.278/1M
from $0.20 at Hugging Face
+39%—
Qwen2.5 72B Instruct 128KCheapest$0.574/1M$0.574/1M——
Qwen3-Coder 30B-A3B Instruct$0.097/1M$0.389/1M
from $0.27 at DevPass (LLM Gateway)
+44%—
Qwen3.5 35B-A3B$0.222/1M$1.78/1M
from $0.451 at AIHubMix
-11%—
GLM-4.5-Air$0.139/1M$0.833/1M
from $0.291 at ZenMux
-24%—
Qwen3 32B$0.139/1M$0.556/1M
from $0.25 at Hugging Face
+122%—
Qwen3.5 27B$0.25/1M$2/1M
from $0.677 at AIHubMix
-17%—
Qwen3 Embedding 0.6BCheapest—$0.01/1M——
GLM 4 32B 0414$0.263/1M$0.263/1M
from $0.08 at AIHubMix
+228%—
Qwen3 Reranker 0.6BCheapest—$0.01/1M——
Hunyuan-A13B-InstructCheapest$0.139/1M$0.556/1M——
Deepseek 3.2$0.278/1M$0.417/1M
from $0.308 at APIMart
+35%—
DeepSeek R1 0528$0.556/1M$2.22/1M
from $1.23 at APIMart
+80%—
DeepSeek V3 0324$0.278/1M$1.11/1M
from $0.822 at APIMart
+35%—
DeepSeek V3.1 Terminus$0.556/1M$1.67/1M
from $0.95 at Hugging Face
+75%—
DeepSeek-V3.2-Exp$0.278/1M$0.417/1M
from $0.308 at APIMart
+35%—
GLM-4.5V$0.139/1M$0.833/1M
from $0.822 at AIHubMix
-54%—
Hy4 preview$0.833/1M$2.50/1M
from $2.25 at OpenRouter
+11%—
Ling Mini 2.0$0.069/1M$0.278/1M
from $0.272 at AIHubMix
+2%—
Ling-flash-2.0$0.139/1M$0.556/1M
from $0.544 at AIHubMix
+2%—
Qwen Image—$0.042/img
from $0.02 at FastRouter
+108%—
Qwen2.5-32B-InstructCheapest$0.175/1M$0.175/1M——
Qwen2.5-72B-Instruct$0.574/1M$0.574/1M
from $0.40 at Deep Infra
+43%—
Qwen2p5 14BCheapest$0.097/1M$0.097/1M——
Qwen3 30B-A3B Instruct 2507$0.097/1M$0.389/1M
from $0.30 at Cortecs
+30%—
Qwen3 Embedding 8BCheapest—$0.039/1M——
Qwen3 Omni 30B A3B ThinkingCheapest$0.097/1M$0.389/1M——
Qwen3 Reranker 8BCheapest—$0.039/1M——
Qwen3 VL 30B A3B InstructCheapest$0.097/1M$0.389/1M——
Qwen3-Reranker-4BCheapest—$0.019/1M——

SiliconFlow at a glance

59 models in total: 45 text, 4 image, 4 embedding, 4 reranking, 2 video. The cheapest is Qwen3 Embedding 0.6B at $0.01 /1M. LongCat-2.0 has the largest context window, 1.05M tokens. The most searched is GLM-5.3, with about 276K Google searches a month. The newest is DeepSeek V4.1 Flash, released Sep 10, 2026.

Cheapest

  1. Qwen3 Embedding 0.6B$0.01/1M
  2. Qwen3 Reranker 0.6B$0.01/1M
  3. Qwen 3 Embedding 4B$0.019/1M
  4. Qwen3-Reranker-4B$0.019/1M
  5. Qwen3 Embedding 8B$0.039/1M

Largest context

  1. LongCat-2.01.05M
  2. GLM-5.31.05M
  3. DeepSeek V4.1 Flash1.05M
  4. DeepSeek V4 Flash1.05M
  5. DeepSeek V4 Pro1.05M

Most searched

  1. GLM-5.3276K
  2. DeepSeek V4.1 Flash138K
  3. Qwen3.8 27B120K
  4. GLM-5.2109K
  5. DeepSeek V4 Flash51K

Newest

  1. DeepSeek V4.1 FlashSep 10, 2026
  2. Hy4 previewAug 27, 2026
  3. GLM-5.3Aug 25, 2026
  4. Qwen3.8 27BAug 5, 2026
  5. LongCat-2.0Jul 5, 2026