SiliconFlow models and pricing

We track 42 models on SiliconFlow (43 listings) from 10 labs. The cheapest paid model is Qwen/Qwen2.5-7B-Instruct, at $0.05 per million input tokens and $0.05 per million output tokens. Input prices range from $0.04 to $2.70 and output prices from $0.05 to $13.50 per million tokens. The largest context window is 1M tokens (GLM-5.3-Flash, GLM-5.3 and 3 other models). Prices last verified 18 Nov 2026.

Prices in USD per million tokens. Official site

Cheapest models on SiliconFlow

Input / output per million tokens, paid models, by combined price.

Newest models on SiliconFlow

By the lab's release date.

All SiliconFlow models and prices

ModelLabInputOutputContextSource
GLM-5.3-Flash
zai-org/GLM-5.3-Flash
Zhipu AI (Z.ai)$0.15$0.501Mmodels.dev
DeepSeek V4 Flash Vision Exp
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
DeepSeek$0.44$1.321Mmodels.dev
GLM-5.3
zai-org/GLM-5.3
Zhipu AI (Z.ai)$1.40$4.401Mmodels.dev
DeepSeek V4 Pro
deepseek-ai/DeepSeek-V4-Pro-0813
DeepSeek$1.32$3.961Mmodels.dev
DeepSeek V4 Pro
deepseek-ai/DeepSeek-V4-Pro
DeepSeek$1.50$3.131Mmodels.dev
Qwen3.8 2.4T A95B
Qwen/Qwen3.8-2.4T-A95B
Alibaba (Qwen)$2$61Mmodels.dev
DeepSeek V4 Flash 0731
deepseek-ai/DeepSeek-V4-Flash-0731
DeepSeek$0.22$0.661Mmodels.dev
Kimi K3
moonshotai/Kimi-K3
Moonshot AI$2.70$13.501Mmodels.dev
Hy3
tencent/Hy3
Tencent (Hunyuan)$0.13$0.53262Kmodels.dev
LongCat-2.0
meituan-longcat/LongCat-2.0
Meituan$0.75$2.951Mmodels.dev
GLM-5.2
zai-org/GLM-5.2
Zhipu AI (Z.ai)$1.30$4.091Mmodels.dev
Kimi K2.7 Code
moonshotai/Kimi-K2.7-Code
Moonshot AI$0.86$3.80262Kmodels.dev
Gemma 4 12B IT
google/gemma-4-12B-it
Google DeepMind$0.10$0.30262Kmodels.dev
MiniMax-M3
MiniMaxAI/MiniMax-M3
MiniMax$0.30$1.201Mmodels.dev
DeepSeek V4 Flash
deepseek-ai/DeepSeek-V4-Flash
DeepSeek$0.13$0.281Mmodels.dev
Qwen3.6 27B
Qwen/Qwen3.6-27B
Alibaba (Qwen)$0.30$3.20262Kmodels.dev
Kimi K2.6
moonshotai/Kimi-K2.6
Moonshot AI$0.77$3.40262Kmodels.dev
Qwen3.6 35B-A3B
Qwen/Qwen3.6-35B-A3B
Alibaba (Qwen)$0.24$1.80262Kmodels.dev
GLM-5.1
zai-org/GLM-5.1
Zhipu AI (Z.ai)$1.19$3.74205Kmodels.dev
Gemma 4 31B IT
google/gemma-4-31B-it
Google DeepMind$0.75$1262Kmodels.dev
Gemma 4 26B A4B IT
google/gemma-4-26B-A4B-it
Google DeepMind$0.14$0.40262Kmodels.dev
GLM-5V-Turbo
zai-org/GLM-5V-Turbo
Zhipu AI (Z.ai)$1.20$4200Kmodels.dev
Qwen3.5 35B-A3B
Qwen/Qwen3.5-35B-A3B
Alibaba (Qwen)$0.24$1.80262Kmodels.dev
Qwen/Qwen3.5-9B
Qwen/Qwen3.5-9B
Alibaba (Qwen)$0.10$0.15262Kmodels.dev
Qwen3.5 122B-A10B
Qwen/Qwen3.5-122B-A10B
Alibaba (Qwen)$0.26$2.08262Kmodels.dev
Qwen3.5 27B
Qwen/Qwen3.5-27B
Alibaba (Qwen)$0.25$2262Kmodels.dev
GLM-5
zai-org/GLM-5
Zhipu AI (Z.ai)$0.95$2.55205Kmodels.dev
Step 3.5 Flash
stepfun-ai/Step-3.5-Flash
StepFun$0.10$0.30262Kmodels.dev
Kimi K2.5
moonshotai/Kimi-K2.5
Moonshot AI$0.45$2.25262Kmodels.dev
DeepSeek V3.2
deepseek-ai/DeepSeek-V3.2
DeepSeek$0.27$0.42164Kmodels.dev
Qwen3 VL 30B A3B Instruct
Qwen/Qwen3-VL-30B-A3B-Instruct
Alibaba (Qwen)$0.29$1262Kmodels.dev
DeepSeek-V3.1
deepseek-ai/DeepSeek-V3.1
DeepSeek$0.27$1164Kmodels.dev
gpt-oss-120b
openai/gpt-oss-120b
OpenAI$0.05$0.45131Kmodels.dev
gpt-oss-20b
openai/gpt-oss-20b
OpenAI$0.04$0.18131Kmodels.dev
Qwen3-30B-A3B-Instruct-2507
Qwen/Qwen3-30B-A3B-Instruct-2507
Alibaba (Qwen)$0.09$0.30262Kmodels.dev
GLM-4.5-Air
zai-org/GLM-4.5-Air
Zhipu AI (Z.ai)$0.14$0.86131Kmodels.dev
DeepSeek-R1-0528
deepseek-ai/DeepSeek-R1
DeepSeek$0.50$2.18164Kmodels.dev
Qwen3 32B
Qwen/Qwen3-32B
Alibaba (Qwen)$0.14$0.57131Kmodels.dev
Qwen3 8B
Qwen/Qwen3-8B
Alibaba (Qwen)$0.06$0.06131Kmodels.dev
Qwen3-Coder 480B-A35B Instruct
Qwen/Qwen3-Coder-480B-A35B-Instruct
Alibaba (Qwen)$0.25$1262Kmodels.dev
Qwen3-Coder 30B-A3B Instruct
Qwen/Qwen3-Coder-30B-A3B-Instruct
Alibaba (Qwen)$0.07$0.28262Kmodels.dev
DeepSeek V3 0324
deepseek-ai/DeepSeek-V3
DeepSeek$0.25$1164Kmodels.dev
Qwen/Qwen2.5-7B-Instruct
Qwen/Qwen2.5-7B-Instruct
Alibaba (Qwen)$0.05$0.0533Kmodels.dev

Frequently asked questions

How much does SiliconFlow cost per million tokens?

Prices on SiliconFlow depend on the model. Across the 42 models we track, input costs $0.04 to $2.70 per million tokens and output costs $0.05 to $13.50 per million tokens. Prices last verified 18 Nov 2026.

What is the cheapest model on SiliconFlow?

Qwen/Qwen2.5-7B-Instruct from Alibaba (Qwen) is the cheapest paid model we track on SiliconFlow, at $0.05 per million input tokens and $0.05 per million output tokens. Next are Qwen3 8B ($0.06 / $0.06) and gpt-oss-20b ($0.04 / $0.18). Prices last verified 18 Nov 2026.

How many models does SiliconFlow offer?

We currently track 42 active models on SiliconFlow from 10 labs, led by Alibaba (Qwen) (14), DeepSeek (8), Zhipu AI (Z.ai) (7) and Moonshot AI (4).

Which model on SiliconFlow has the largest context window?

GLM-5.3-Flash, GLM-5.3 and 3 other models share the largest context window we track on SiliconFlow: 1,049,000 tokens (1M).