Get started

Serverless Inference

Frontier models, on Swedish infrastructure

OpenAI-compatible API for leading open models. No data retention, no training on your data, and new models within days of release.

Serverless Inference

Works with your OpenAI client

Point your existing OpenAI client at Berget AI. Same endpoints, same SDKs, and same streaming.

Read the docs
app.ts
const client = new OpenAI({
  baseURL: 'https://api.berget.ai/v1',
  apiKey: 'YOUR_API_KEY'
});

const res = await client.chat.completions.create({
  model: 'gemma-4-31B-it',
  messages: [{ role: 'user', content: 'Deploy app' }]
});

Models

Pick the right model for the job

Every model we run, with live pricing and capabilities straight from the API. Whichever you choose, your traffic never leaves Sweden.

Loading models…

Simple, transparent pricing

Pay per token, or pick a plan for predictable spend. No egress fees.

Trial

€0 / month

For the hobbyist

  • €5 free starting credits

  • Basic rate limits*

  • Community support

  • No monthly cost

Starter

€25 / month

For small projects

  • €25 monthly top-up

  • Increased rate limits*

  • Email support

  • Automatic billing

Team

€50 / month

For developer teams

  • €55 monthly top-up

  • Higher rate limits*

  • Priority support

  • 10% extra credits

Enterprise

€500 / month

For high-volume production

  • €550 monthly top-up

  • Maximum rate limits*

  • Dedicated support

  • 10% extra credits

  • Invoice and Peppol billing

* Rate limits are shared per account.

Want to compare pricing across all our models in detail? See pricing

Deployment options

Choose between shared and dedicated deployment, depending on latency needs, traffic patterns, and how much infrastructure control you need.

You are here

Serverless Inference

Pay per token on our shared fleet in Sweden. OpenAI-compatible, live in minutes.

Learn more

Dedicated Inference

Reserved GPUs running your model, with guaranteed throughput and a contracted SLA.

Learn more