Skip to content

Inference Net

Pricing page

94 listings across 77 models

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

Sold by Inference Net

26 listings on this page sold by Inference Net.

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
GPT-5.6 Luna
——Not published by the provider
MiniMax M3.1 Flash
——Not published by the providerNot measuredNot measured
Gemini 3.6 Flash
——Not published by the provider
GLM 5.2
——Not published by the provider
GLM 5.2glm-5.2-fast · fast
——Not published by the provider
Claude Sonnet 4.6
——Not published by the provider
GLM 5.3 Flash
——Not published by the provider
Kimi K2.6
——Not published by the provider
DeepSeek V4 Flash 0731
——Not published by the provider
Gemini 3 Flashgemini-3-flash-preview
——Not published by the provider
DeepSeek V4 Pro
——Not published by the provider
GLM 5
——Not published by the provider
Qwen3.7 Plus
——Not published by the provider
DeepSeek V4 Flash
——Not published by the provider
Gemini 2.5 Pro
——Not published by the provider
Kimi K2.5
——Not published by the provider
Gemini 3.5 Flash Lite
——Not published by the provider
Gemini 3.1 Flash Lite
——Not published by the provider
DeepSeek V3.2
——Not published by the providerNot measured
GPT-5 mini
——Not published by the provider
Qwen3 Embedding 4B
Not enough data yet$0.01—32KNot enough data yetNot measuredNot measured
Claude Haiku 4.5
——Not published by the provider
Gemini 2.5 Flash
——Not published by the provider
GPT 4.1
——Not published by the provider
Nemotron 3 Super
——Not published by the providerNot measured
GPT-4.1 mini
——Not published by the providerNot measured

Run by Inference Net

5 listings on this page where Inference Net 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
MiniMax M3.1 Flash
 Hugging Face$0.15$0.601MNot measuredNot measured
MiniMax M3.1 Flash
 Llmgateway$0.10cache read $0.005$0.50Not published by the providerNot measuredNot measured
GLM 5.3 Flash
 Hugging Face$0.108$0.351M
GLM 5.3 Flash
 Llmgateway$0.09cache read $0.02$0.28Not published by the provider
DeepSeek V4 Flash
 Llmgateway$0.23cache read $0.0028$0.62Not published by the provider

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

How this data works