Skip to content

Berget AI

Pricing page

21 listings across 17 models

Data policies

from the provider's published policies

Headquarters: SE

On training
We don't have their wording on this. Their policy: berget.ai/en/terms, Berget AI privacy policy
On keeping your data

For the avoidance of doubt - Berget will never store any of the actual prompt content used as model input, or any of the output content generated by the LLMs we host.

Source: berget.ai/en/terms

On where data is processed

We see no reason whatsoever to transfer data outside of the EEA, but in the case that we should be ordered by a customer to transfer personal data outside the European Economic Area (EEA), we ensure appropriate safeguards, such as: Standard Contractual Clauses (SCCs) approved by the European Commis…

Possible sources (2)

We take these statements from Berget AI'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.

Sold by Berget AI

17 listings sold by Berget AI.

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 K3.1 ProMXFP4
Not published by the provider
Kimi K3
$3.3645cache read $1.0094$16.823328K
GLM 5.2
$1.54$4.84524K
GLM 5.3 FlashFP8
1M
Qwen 3.8 27BQwen/Qwen3.8-27B-FP8 · fp8
$0.46$3.48262KNot measured
Gemma 4 31B ITBF16
128K
Mistral Small 3.2 24B Instructmistralai/Mistral-Small-3.2-24B-Instruct-2506 · 2506 · BF16
Not enough data yet32KNot measuredNot measured
Not enough data yetNot published by the providerNot enough data yetNot measuredNot measured
Not enough data yet—Not published by the providerNot enough data yetNot measuredNot measured
Qwen3.5 2BBF16
Not enough data yet—Not published by the providerNot enough data yetNot measuredNot measured
clef flashBF16
Doesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this modelNot published by the providerDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
layaFP16
Doesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this modelNot published by the providerDoesn’t apply to this modelDoesn’t apply to this modelDoesn’t apply to this model
BGE Reranker v2 M3FP16
Not enough data yetNot enough data yetNot published by the providerNot enough data yetNot measuredNot measured
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Kblab Kb Whisper LargeKBLab/kb-whisper-large · FP16
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
pianissimoFP16
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured

Run by Berget AI

4 listings where Berget AI 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
 Cortecs AI——1M
 Cortecs AI——1M
 Cortecs AI——262K
Mistral Small 3.2 24B Instructmistral-small-3.2-24b-instruct-2506 · 2506
 Cortecs AINot enough data yet——131KNot measuredNot measured

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

Around the web

  • Berget AI
    Berget AI has 20 repositories available. Berget AI models inside Pi with Swedish EU-jurisdiction. The …Berget AI has 20 repositories available. Berget AI models inside Pi with Swedish EU-jurisdiction. The open-source app everyone uses to manage ...

    github.com

    Repository
  • Berget AI - We champion AI sovereignty to unlock innovation ...
    When public cloud isn't an option, Berget AI is your secure and scalable alternative. We …When public cloud isn't an option, Berget AI is your secure and scalable alternative. We combine the benefits of cloud services and on-premises solutions.

    berget.ai

  • Berget AI
    Christian Landgren (Berget AI), Berget AI are teaming up for an evening of talks, food, …Christian Landgren (Berget AI), Berget AI are teaming up for an evening of talks, food, and mingling around the vastness that is AI today.

    se.linkedin.com

  • Berget AI | European AI & Machine Learning Alternative
    Berget AI: Provides EU-compliant AI inference services and infrastructure designed specifically for developers to foster …Berget AI: Provides EU-compliant AI inference services and infrastructure designed specifically for developers to foster European innovation.

    europeantechmap.eu

  • "Start by just starting", how and why we built Berget, Sovereign ...
    Christian Landgren, Co-Founder of Berget AI, shares the remarkable journey behind building Berget AI — …Christian Landgren, Co-Founder of Berget AI, shares the remarkable journey behind building Berget AI — fully hosted and operated within Sweden. ...

    youtube.com

  • Berget AI raises €2M to challenge US tech giants with EU- ...
    Berget AI, a Swedish startup, has raised 24 million kronor just one year after its …Berget AI, a Swedish startup, has raised 24 million kronor just one year after its founding. The funding came from prominent Swedish venture capital firms.

    app.dealroom.co

  • Berget AI 2026 Company Profile
    Berget AI Developer of an AI infrastructure software designed for developers to deploy large language …Berget AI Developer of an AI infrastructure software designed for developers to deploy large language models (LLMs). Berget AI has raised $2.64M.

    pitchbook.com

How this data works