# Berget AI | European inference provider profile and prices

[Directories](/directories/) › [European Inference](/eu/) › Berget AI

![Berget AI logo](/logos/berget.png)

Verified

Berget AI is a Sweden-based provider in the Sovereign cloud category with 15 listed models. No cached-input rate is published.

EU-owned EU hosting Sovereign cloud

[Visit website ↗](https://berget.ai) [API docs ↗](https://api.berget.ai/v1)

Overview Models Pricing Infrastructure Access Compliance Benchmarks Performance

## At a glance

Record

Ownership

Berget AI AB (founded 2024)

Headquarters

Sweden

Hosting region

EU (Sweden)

Founded

2024

Website

[berget.ai](https://berget.ai)

## Summary

Scope

Berget AI is a Sweden-based provider in the Sovereign cloud category with 15 listed models. No cached-input rate is published.

Own hardware in Sweden; prices exclude VAT (25% SE consumers, 0% EU business reverse charge).

[Source: berget.ai ↗](https://berget.ai) · Updated Nov 4, 2026

### API access

OpenAI-compatible

### Access

APISubscription

### KYC

Not published

### Compliance

GDPRDPA published100% fossil-free electricityDPA

## Key models

15 listed

gpt-oss-120b , context · per 1M tokens Inference €0.2 / €0.75

Mistral Medium 3.5 128B , context · per 1M tokens Inference €1.5 / €5

Mistral Small 3.2 24B , context · per 1M tokens Multimodal €0.3 / €0.3

GLM-4.7 FP8 , context · per 1M tokens Inference €0.7 / €2.5

Gemma 4 31B IT , context · per 1M tokens Multimodal €0.25 / €0.5

Llama 3.3 70B Instruct , context · per 1M tokens Inference €0.9 / €0.9

Llama 3.1 8B Instruct , context · per 1M tokens Inference €0.2 / €0.2

GLM-5.3 Flash 1M context · per 1M tokens Inference €0.25 / €0.5

Kimi K3 1M context · per 1M tokens Multimodal €3 / €15

multilingual-e5-large-instruct , context · per 1M tokens Embedding €0.03 / €0

multilingual-e5-large , context · per 1M tokens Embedding €0.03 / €0

bge-reranker-v2-m3 , context · per 1M tokens Rerank €0.1 / €0

KB-Whisper Large , context · per 1k minutes Speech €3 / €0

NB-Whisper Large , context · per 1k minutes Speech €3 / €0

Faster-Whisper Large v3 , context · per 1k minutes Speech €3 / €0

## Pricing

List rates · EUR

Model Type Input price Caching price Output price

gpt-oss-120b, context · per 1M tokens Inference €0.2 \- €0.75

Mistral Medium 3.5 128B, context · per 1M tokens Inference €1.5 \- €5

Mistral Small 3.2 24B, context · per 1M tokens Multimodal €0.3 \- €0.3

GLM-4.7 FP8, context · per 1M tokens Inference €0.7 \- €2.5

Gemma 4 31B IT, context · per 1M tokens Multimodal €0.25 \- €0.5

Llama 3.3 70B Instruct, context · per 1M tokens Inference €0.9 \- €0.9

Llama 3.1 8B Instruct, context · per 1M tokens Inference €0.2 \- €0.2

GLM-5.3 Flash1M context · per 1M tokens Inference €0.25 \- €0.5

Kimi K31M context · per 1M tokens Multimodal €3 \- €15

multilingual-e5-large-instruct, context · per 1M tokens Embedding €0.03 \- €0

multilingual-e5-large, context · per 1M tokens Embedding €0.03 \- €0

bge-reranker-v2-m3, context · per 1M tokens Rerank €0.1 \- €0

KB-Whisper Large, context · per 1k minutes Speech €3 \- €0

NB-Whisper Large, context · per 1k minutes Speech €3 \- €0

Faster-Whisper Large v3, context · per 1k minutes Speech €3 \- €0

List rates. Cached input shown where published; "-" means the provider does not publish a cache rate. Units follow the source rate card.

## Infrastructure

Hosting

Region**EU**

Cities**Sweden**

Provider group**Sovereign cloud**

ZDR**yes**

DPA**Available**

Cached input policy**No cached-input rate published.**

## Access

API & payments

API shape**OpenAI-compatible**

Access**API, Subscription**

KYC**Not published**

Cached input policy**No cached-input rate published.**

## Compliance

Source-backed

DPA**Available**

ZDR**yes**

Retention**ZDR: yes. DPA published.**

Certifications

GDPRDPA published100% fossil-free electricityDPA

## Benchmarks

Coming soon

Coming soon.

## Performance

Coming soon

Latency

### Time to first token

Median and p95 response times for short and long prompts, measured from repeatable probes rather than vendor claims.

Coming soon

Throughput

### Tokens per second

Streaming output rate and request throughput under steady load, with concurrency and context length recorded.

Coming soon

Efficiency

### Cost per workload

Blended cost for a fixed workload, including cache reads and output tokens, so speed and price can be compared together.

Coming soon

Independent performance probes are being added. Vendor-reported numbers are not mixed into this section.

[PreviousTensorX](/eu/providers/tensorx) [Nextevroc](/eu/providers/evroc)