Skip to content

SiliconFlow

Pricing page

196 listings across 91 models

Page 2 of 4. The lists below split this page's listings into those sold by SiliconFlow, run by SiliconFlow, or sent to SiliconFlow by a marketplace.

Sold by SiliconFlow

21 listings on this page sold by SiliconFlow.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Kimi K2.7 Codefp8
$0.8592cache read $0.1799$3.80262K
GLM 5V Turbo
$1.20cache read $0.24$4.00200KNot measuredNot measured
MiniMax M3fp8
$0.30cache read $0.06$1.201M
Qwen3.5 122B-A10Bfp8
$0.26$2.08262KNot measuredNot measured
Step 3.5 Flash
$0.10$0.30262KNot measuredNot measured
Qwen3.5 27Bfp8
$0.25$2.00262KNot measured
DeepSeek V3.2fp8
$0.27cache read $0.135$0.42164KNot measured
Gemma 4 26B A4Bgoogle/gemma-4-26B-A4B-it · fp8
$0.14cache read $0.05$0.40262K
Qwen3 Embedding 4B
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
DeepSeek V3.2 Exp
$0.27$0.41164KNot measured
Qwen3.6 27Bfp8
$0.30$3.20262KNot measured
MiniMax M2.5
$0.30cache read $0.03$1.20197KNot measured
DeepSeek R1
$0.50$2.18164K
DeepSeek V3.1 Terminusfp8
$0.27$1.00164KNot measured
Gemma 4 12B It
Not enough data yet$0.10$0.30262KNot enough data yetNot measuredNot measured
Qwen3.5 35B A3Bfp8
$0.24cache read $0.15$1.80262K
Qwen3.6 35B A3Bfp8
$0.24cache read $0.15$1.80262KNot measured
Qwen3 VL 32B Thinking
Not enough data yet$0.20$1.50262KNot enough data yetNot measuredNot measured
DeepSeek V3.1fp8
$0.27$1.00164KNot measured
Not enough data yet$0.21$0.57262KNot enough data yetNot measuredNot measured
Qwen3 CoderQwen/Qwen3-Coder-480B-A35B-Instruct
$0.25$1.00262KNot measured

Run by SiliconFlow

35 listings on this page where SiliconFlow runs the model. Another provider sells these listings.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Kimi K2.7 Codefp8 · 🇸🇬 SG
 NanoGPT$0.9021cache read $0.1889$3.99Not published by the provider
MiniMax M3fp8 · 🇸🇬 SG
 NanoGPT$0.63cache read $0.126$2.52Not published by the provider
Qwen3.5 122B-A10Bfp8 · 🇸🇬 SG
 NanoGPT$0.273$2.184Not published by the providerNot measuredNot measured
Qwen3.5 27Bfp8 · 🇸🇬 SG
 NanoGPT$0.2625$2.10Not published by the providerNot measured
DeepSeek V3.2fp8 · 🇸🇬 SG
 NanoGPT$0.272cache read $0.147$0.84Not published by the providerNot measured
Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-it · fp8 · 🇸🇬 SG
 NanoGPT$0.147cache read $0.0525$0.42Not published by the provider
DeepSeek V3.2 Expfp8
 OpenRouter$0.27$0.41164KNot measured
Qwen3.6 27Bfp8 · 🇸🇬 SG
 NanoGPT$0.315$3.36Not published by the providerNot measured
DeepSeek R1deepseek-ai/DeepSeek-R1-0528 · 0528 · fp8 · 🇸🇬 SG
 NanoGPT$0.525$2.289Not published by the provider
LongCat 2.0🇸🇬 SG
 NanoGPTNot enough data yet$0.7875cache read $0.0158$3.0975Not published by the providerNot enough data yetNot measuredNot measured
DeepSeek V3.1 Terminusfp8 · 🇸🇬 SG
 NanoGPT$0.2835$1.05Not published by the providerNot measured
Qwen3.5 35B A3Bfp8 · 🇸🇬 SG
 NanoGPT$0.252cache read $0.1575$1.89Not published by the provider
Qwen3.6 35B A3Bfp8 · 🇸🇬 SG
 NanoGPT$0.252cache read $0.1575$1.89Not published by the providerNot measured
DeepSeek V3.1fp8 · 🇸🇬 SG
 NanoGPT$0.2835$1.05Not published by the providerNot measured
Show all 35 listings

Showing 14 of 35: one listing for each model.

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works