Skip to content

Inference Net

Pricing page

94 listings across 77 models

Data policies

from the provider's published policies

Headquarters: USPrivacy policyTerms of serviceStatus page

On training

We do not use your data to train AI models.

Source: Inference.net privacy policy

On where data is processed

your personal information may be transferred to, and/or processed in, the United States

Possible sources (2)

We take these statements from Inference Net'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 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-6 Astra
——Not published by the provider
——Not published by the provider
GPT-6.1 Sol
——Not published by the provider
Claude Opus 5
——Not published by the provider
Claude Fable 5
——Not published by the provider
——Not published by the provider
GPT-6 Sol
——Not published by the provider
GPT-5.6 Sol
——Not published by the provider
GPT 5.5
——Not published by the provider
Claude Opus 4.8
——Not published by the provider
——Not published by the provider
Kimi K3
——Not published by the provider
Kimi K3kimi-k3-fast · fast
——Not published by the provider
Gemini 3.7 Flash
——Not published by the provider
Claude Opus 4.7
——Not published by the provider
GLM 5.3
——Not published by the provider
Grok 4.6
——Not published by the provider
——Not published by the provider
Claude Opus 4.6
——Not published by the provider
——Not published by the provider
GPT 5.4
——Not published by the provider
Grok 4.5
——Not published by the provider
——Not published by the provider
Gemini 3.5 Flash
——Not published by the provider
GPT-5.6 Terra
——Not published by the provider
GPT-6 Luna
——Not published by the provider

Run by Inference Net

10 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
 Hugging Face$1.80$9.001M
 Hugging Face$0.08$0.6661M
Kimi K3
 Hugging Face$0.245$15.751M
GLM 5.3
 Hugging Face$0.084$3.601M
 Hugging Face$0.103$0.601M
Show all 10 listings

Showing 5 of 10: one listing for each model.

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

How this data works