Skip to content

SiliconFlow

Pricing page

196 listings across 91 models

Data policies

from the provider's published policies

Headquarters: SGDisclosed data centres: USPrivacy policyTerms of service

On training
We don't have their wording on this. Their policy: SiliconFlow privacy policy
Other statements

Personal Data Protection Act 2012 of Singapore

Source: SiliconFlow privacy policy

We take these statements from SiliconFlow's own published policies each time we refresh the data, so they can change or disappear when those pages do. Check with the provider before you rely on any of this.

Page 1 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

24 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
——Not published by the provider
——Not published by the provider
Kimi K3
$2.70cache read $0.27$13.501M
Qwen3.8 MaxQwen/Qwen3.8-2.4T-A95B · fp8
$2.00cache read $0.25$6.001M
GLM 5.3fp8
$1.40cache read $0.26$4.401M
DeepSeek V4.1 Flashfp8
——Not published by the provider
DeepSeek V4 Pro 0813fp8
$1.32cache read $0.044$3.961M
$0.44cache read $0.028$1.321MNot measuredNot measured
Hy4 previewfp8
——Not published by the providerNot measured
——Not published by the providerNot measuredNot measured
GLM 5.2fp8
$1.302cache read $0.26$4.0921M
GLM 5.3 Flashfp8
$0.15cache read $0.03$0.501M
Kimi K2.6fp8
$0.77cache read $0.14$3.40262K
DeepSeek V4 Flash 0731fp8
$0.22cache read $0.014$0.661M
Not enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
GLM 5.1fp8
$1.19cache read $0.60$3.74205K
$1.5016cache read $0.135$3.1351M
$0.39$2.34262K
GLM 5fp8
$0.95cache read $0.20$2.55205K
Qwen 3.8 27Bfp8
——Not published by the providerNot measured
DeepSeek V4 Flash
$0.13cache read $0.028$0.281M
Kimi K2.5int4
$0.45cache read $0.07$2.25262K
Gemma 4 31B ITfp8
$0.75cache read $0.25$1.00262K
Hy3 (Deep Infra)tencent/Hy3
$0.132cache read $0.033$0.528262KNot measuredNot measured

Run by SiliconFlow

48 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
DeepSeek V4.1 Flash 1017fp8 · 🇸🇬 SG
 NanoGPT$0.1575cache read $0.0032$0.63Not published by the provider
Qwen3.8 Maxfp8 · 🇸🇬 SG
 NanoGPT$2.10cache read $0.2625$6.30Not published by the provider
GLM 5.3fp8 · 🇸🇬 SG
 NanoGPT$0.735cache read $0.1365$1.995Not published by the provider
DeepSeek V4.1 Flashfp8 · 🇸🇬 SG
 NanoGPT$0.315cache read $0.0063$1.26Not published by the provider
DeepSeek V4 Pro 0813fp8 · 🇸🇬 SG
 NanoGPT$1.386cache read $0.0462$4.158Not published by the provider
DeepSeek V4 Flash Vision Expfp8 · 🇸🇬 SG
 NanoGPT$0.462cache read $0.0294$1.386Not published by the providerNot measuredNot measured
Hy4 previewfp8 · 🇸🇬 SG
 NanoGPT$0.8757cache read $0.0441$2.6261Not published by the providerNot measured
GLM 5.2fp8 · 🇸🇬 SG
 NanoGPT$0.6836cache read $0.1365$2.1483Not published by the provider
GLM 5.3 Flashfp8 · 🇸🇬 SG
 NanoGPT$0.105cache read $0.0315$0.42Not published by the provider
Kimi K2.6fp8
 OpenRouter$0.77cache read $0.14$3.40262K
DeepSeek V4 Flash 0731fp8 · 🇸🇬 SG
 NanoGPT$0.231cache read $0.0294$0.693Not published by the provider
DeepSeek V4.1 Flash 0910deepseek/deepseek-v4.1-flash · fp8
 OpenRouterNot enough data yet$0.30cache read $0.006$1.201MNot enough data yetNot measuredNot measured
GLM 5.1fp8 · 🇸🇬 SG
 NanoGPT$1.2495cache read $0.63$3.927Not published by the provider
DeepSeek V4 Profp8
 OpenRouter$0.90cache read $0.08$1.701M
GLM 5fp8 · 🇸🇬 SG
 NanoGPT$0.9975cache read $0.21$2.6775Not published by the provider
Qwen 3.8 27Bfp8 · 🇸🇬 SG
 NanoGPT$0.4463cache read $0.0893$2.6775Not published by the providerNot measured
DeepSeek V4 Flashdeepseek/deepseek-v4-flash-latest · latest · fp8 · 🇸🇬 SG
 NanoGPT$0.1575cache read $0.0032$0.63Not published by the provider
Kimi K2.5int4 · 🇸🇬 SG
 NanoGPT$0.525cache read $0.1575$2.625Not published by the provider
Gemma 4 31B ITfp8 · 🇸🇬 SG
 NanoGPT$0.7875cache read $0.2625$1.05Not published by the provider
Show all 48 listings

Showing 19 of 48: one listing for each model.

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

Around the web

  • Quickstart - SiliconFlow
    Log in to the platform 2. View model lists and details 3. Experience GenAI capabilities …Log in to the platform 2. View model lists and details 3. Experience GenAI capabilities in the playground 4. Use SiliconFlow API to call GenAI capabilities

    docs.siliconflow.cn

    Docs
  • SiliconFlow

    SiliconFlow builds scalable, standardized, and high-performance AI infrastructure. language, speech, vision, and multimodal domains.

    github.com

    Repository
  • SiliconFlow (@SiliconFlowAI) / Posts / X
    Fast AI inference. 200+ models via one API. OpenAI/Anthropic compatible. Today, we are the largest …Fast AI inference. 200+ models via one API. OpenAI/Anthropic compatible. Today, we are the largest AI marketplace & gateway, processing 10T+ tokens daily on ...

    x.com

  • SiliconFlow
    It is designed for coding, tool use, deep research, and long-horizon agentic workflows, unifying planning, …It is designed for coding, tool use, deep research, and long-horizon agentic workflows, unifying planning, code implementation, debugging, and iteration into a ...Read more

    openrouter.ai

  • SiliconFlow: Models Intelligence, Performance & Price
    Analysis of SiliconFlow's models across key metrics including quality, price, output speed, latency, context window …Analysis of SiliconFlow's models across key metrics including quality, price, output speed, latency, context window & more.

    artificialanalysis.ai

  • SiliconFlow Alternatives: 85 Open-Source & API ...
    SiliconFlow is an inference platform that serves open-source LLMs alongside image, video, and audio models …SiliconFlow is an inference platform that serves open-source LLMs alongside image, video, and audio models through a single OpenAI-compatible API.Read more

    infrabase.ai

How this data works