SiliconFlow

Inference provider

Pricing page ↗ SiliconFlow's own price list, link checked 2026-10-19. Check the prices below against it.

Endpoints
63
Models
63

Models served

63 shown

ModelCreatorTypeIn $/1MOut $/1MContextMax outputToolsRegion
DeepSeek R1
deepseek-ai/DeepSeek-R1
DeepSeekChat$0.50$2.18164K164KRegion not stated
DeepSeek R1 0528
deepseek/deepseek-r1-0528
DeepSeekChat$0.50$2.18164K147KRegion not stated
DeepSeek V3
deepseek-ai/DeepSeek-V3
DeepSeekChat$0.25$1.00164K164KRegion not stated
DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324
DeepSeekChat$0.25$1.00164K147KRegion not stated
DeepSeek V3.1
deepseek/deepseek-chat-v3.1
DeepSeekChat$0.27$1.00164K147KRegion not stated
DeepSeek V3.1
deepseek-ai/DeepSeek-V3.1
DeepSeekChat$0.27$1.00164K164KRegion not stated
DeepSeek V3.2 Exp
deepseek-ai/DeepSeek-V3.2-Exp
DeepSeekChat$0.27$0.41164K164KRegion not stated
DeepSeek V4 Flash
deepseek-ai/DeepSeek-V4-Flash
DeepSeekChat$0.13$0.281M384KRegion not stated
DeepSeek V4 Flash Latest
deepseek-ai/DeepSeek-V4-Flash-0731
DeepSeekChat$0.22$0.661M384KRegion not stated
DeepSeek V4 Flash Vision Exp
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
DeepSeekChat$0.44$1.321M384KRegion not stated
DeepSeek V4 Pro
deepseek-ai/DeepSeek-V4-Pro
DeepSeekChat$1.50$3.141M384KRegion not stated
DeepSeek V4 Pro 0813
deepseek-ai/DeepSeek-V4-Pro-0813
DeepSeekChat$1.32$3.961M384KRegion not stated
DeepSeek V4.1 Flash
deepseek/deepseek-v4.1-flash-20260910
DeepSeekChat$0.30$1.201.05M393KRegion not stated
deepseek-v3.1-terminus
deepseek-ai/DeepSeek-V3.1-Terminus
DeepSeekChat$0.27$1.00164K164KRegion not stated
deepseek-v3.2
deepseek-ai/DeepSeek-V3.2
DeepSeekChat$0.27$0.42164K164KRegion not stated
Gemma 4 12B IT
google/gemma-4-12B-it
GoogleChat$0.10$0.30262K262KRegion not stated
Gemma 4 26B A4B IT
google/gemma-4-26B-A4B-it
GoogleChat$0.12$0.40262K262KRegion not stated
Gemma-4-31B-IT
google/gemma-4-31B-it
GoogleChat$0.13$0.40262K262KRegion not stated
GLM-4.5-Air
zai-org/GLM-4.5-Air
Z.ai (Zhipu AI)Chat$0.14$0.86131K131KRegion not stated
GLM-5
zai-org/GLM-5
Z.ai (Zhipu AI)Chat$0.95$2.55205K205KRegion not stated
GLM-5.1
zai-org/GLM-5.1
Z.ai (Zhipu AI)Chat$1.19$3.74205K131KRegion not stated
GLM-5.2
zai-org/GLM-5.2
Z.ai (Zhipu AI)Chat$1.30$4.091.05M262KRegion not stated
GLM-5.3
zai-org/GLM-5.3
Z.ai (Zhipu AI)Chat$1.40$4.401.05M262KRegion not stated
GLM-5.3-Flash
zai-org/GLM-5.3-Flash
Z.ai (Zhipu AI)Chat$0.15$0.501.05M262KRegion not stated
GLM-5V-Turbo
zai-org/GLM-5V-Turbo
Z.ai (Zhipu AI)Chat$1.20$4.00200K131KRegion not stated
GPT OSS 20B
openai/gpt-oss-20b
OpenAIChat$0.04$0.18131K8KRegion not stated
GPT-OSS 120B
openai/gpt-oss-120b
OpenAIChat$0.05$0.45131K8KRegion not stated
Hunyuan A13B Instruct
tencent/Hunyuan-A13B-Instruct
TencentChat$0.14$0.57131K131KRegion not stated
Hy3
tencent/Hy3
TencentChat$0.132$0.528262K262KRegion not stated
Hy4 preview
tencent/hy4-preview-20260827
TencentChat$0.834$2.501.05M262KRegion not stated
Kimi K2.6
moonshotai/Kimi-K2.6
Moonshot AIChat$0.77$3.40262K262KRegion not stated
Kimi K2.7 Code HighSpeed
moonshotai/Kimi-K2.7-Code
Moonshot AIChat$0.859$3.80262K262KRegion not stated
Kimi K3
moonshotai/Kimi-K3
Moonshot AIChat$2.70$13.501.05M262KRegion not stated
Ling-flash-2.0
inclusionAI/Ling-flash-2.0
inclusionAIChat$0.14$0.57131K131KRegion not stated
LongCat-2.0
meituan-longcat/LongCat-2.0
MeituanChat$0.75$2.951.05M131KRegion not stated
MiniMax-M2.5
MiniMaxAI/MiniMax-M2.5
MiniMaxChat$0.30$1.20197K131KRegion not stated
MiniMax-M3
MiniMaxAI/MiniMax-M3
MiniMaxChat$0.30$1.201.05M131KRegion not stated
Moonshot Kimi K2.5
moonshotai/Kimi-K2.5
Moonshot AIChat$0.45$2.25262K262KRegion not stated
Nex-N2-Pro
nex-agi/Nex-N2-Pro
Nex AGIChat$0.50$2.50262K256KRegion not stated
Qwen 3.5 9B (Q4_K_M)
Qwen/Qwen3.5-9B
Alibaba (Qwen)Chat$0.10$0.15262K262KRegion not stated
Qwen2.5 72B Instruct
Qwen/Qwen2.5-72B-Instruct
Alibaba (Qwen)Chat$0.59$0.5933K4KRegion not stated
Qwen2.5 7B Instruct
Qwen/Qwen2.5-7B-Instruct
Alibaba (Qwen)Chat$0.05$0.0533K4KRegion not stated
Qwen3 14B
Qwen/Qwen3-14B
Alibaba (Qwen)Chat$0.07$0.28131K131KRegion not stated
Qwen3 30B A3B Instruct 2507
Qwen/Qwen3-30B-A3B-Instruct-2507
Alibaba (Qwen)Chat$0.09$0.30262K262KRegion not stated
Qwen3 32B
Qwen/Qwen3-32B
Alibaba (Qwen)Chat$0.14$0.57131K131KRegion not stated
Qwen3 8B
Qwen/Qwen3-8B
Alibaba (Qwen)Chat$0.06$0.06131K131KRegion not stated
Qwen3 Embedding 8B
qwen/qwen3-embedding-8b
Alibaba (Qwen)Embedding$0.04$032.8K29.5KRegion not stated
Qwen3 VL 30B A3B Instruct
Qwen/Qwen3-VL-30B-A3B-Instruct
Alibaba (Qwen)Chat$0.29$1.00262K262KRegion not stated
Qwen3 VL 8B Instruct
Qwen/Qwen3-VL-8B-Instruct
Alibaba (Qwen)Chat$0.18$0.68262K262KRegion not stated
Qwen3-Coder 30B-A3B Instruct
Qwen/Qwen3-Coder-30B-A3B-Instruct
Alibaba (Qwen)Chat$0.07$0.28262K262KRegion not stated
Qwen3-Coder 480B-A35B Instruct
Qwen/Qwen3-Coder-480B-A35B-Instruct
Alibaba (Qwen)Chat$0.25$1.00262K262KRegion not stated
Qwen3-Vl 30b A3b Thinking
Qwen/Qwen3-VL-30B-A3B-Thinking
Alibaba (Qwen)Chat$0.29$1.00262K262KRegion not stated
Qwen3-VL-32B-Instruct
Qwen/Qwen3-VL-32B-Instruct
Alibaba (Qwen)Chat$0.20$0.60262K262KRegion not stated
Qwen3-VL-32B-Thinking
Qwen/Qwen3-VL-32B-Thinking
Alibaba (Qwen)Chat$0.20$1.50262K262KRegion not stated
Qwen3.5 122B-A10B
Qwen/Qwen3.5-122B-A10B
Alibaba (Qwen)Chat$0.26$2.08262K262KRegion not stated
Qwen3.5 27B
Qwen/Qwen3.5-27B
Alibaba (Qwen)Chat$0.25$2.00262K262KRegion not stated
Qwen3.5 35B-A3B
Qwen/Qwen3.5-35B-A3B
Alibaba (Qwen)Chat$0.24$1.80262K262KRegion not stated
Qwen3.5 397B-A17B
Qwen/Qwen3.5-397B-A17B
Alibaba (Qwen)Chat$0.39$2.34262K262KRegion not stated
Qwen3.6 27B
Qwen/Qwen3.6-27B
Alibaba (Qwen)Chat$0.30$3.20262K262KRegion not stated
Qwen3.6 35B-A3B
Qwen/Qwen3.6-35B-A3B
Alibaba (Qwen)Chat$0.20$1.60262K262KRegion not stated
Qwen3.8 2.4T A95B (NVFP4)
Qwen/Qwen3.8-2.4T-A95B
Alibaba (Qwen)Chat$2.00$6.001.05M131KRegion not stated
Seed-OSS-36B-Instruct
ByteDance-Seed/Seed-OSS-36B-Instruct
ByteDance SeedChat$0.21$0.57262K262KRegion not stated
Step 3.5 Flash
stepfun-ai/Step-3.5-Flash
StepFunChat$0.10$0.30262K262KRegion not stated

One row per model and variant. Dated pins appear on the model page, not as separate rows. Prices are indicative; verify with the provider.