Berget AI docs
European AI infrastructure that's GDPR-compliant by design
Berget AI runs open-source models on European infrastructure, so your data stays in the EU and your team stays in control.
What is Berget AI?
An overview of what Berget AI is and why it's built on European infrastructure
Quickstart
Make your first API call to Berget AI Serverless Inference
Models
Browse and understand the models available on Berget AI.
Models overview
Available models for Berget AI serverless inference
Model capabilities
Capability matrix for Berget AI language models, including tool use, JSON output, streaming, multimodal input, and throughput
Choose a language model
A decision process for picking the right Berget AI language model for your use case
Model lifecycle
The statuses a model goes through in the Berget AI catalogue (Preview, Active, Deprecated, and Retired) and what each status means for your integrations
Model chains
How combining specialised models in sequence can outperform a single large model, and when to use this pattern
How we select models
The principles behind the Berget AI model catalogue: why we prefer open models, how we evaluate them, and what we optimise for
Integrations
Connect Berget AI to the tools you already use.
Get started with Cline in VS Code and Berget AI
Install Cline, connect it to Berget AI, and write your first AI-assisted code, all without your data leaving Europe
Get started with OpenCode and Berget AI
Use the Berget AI CLI to set up OpenCode, connect it to Berget AI, and run your first AI-assisted coding session on Swedish infrastructure.
Get started with Pi and Berget AI
Use the Berget AI CLI to set up Pi, connect it to Berget AI, and run your first AI-assisted coding session on Swedish infrastructure.