Solheim AI

Private EU-hosted LLM instances billed at a flat monthly fee rather than per token

Solheim rents a private LLM instance on EU hardware for a flat monthly fee instead of billing per token. Each project gets one endpoint and one key, sized by two numbers: how many requests run concurrently, and how much context each one gets.

The API is OpenAI-compatible, so existing clients and BYOK editor integrations work unmodified. Models are open-weight and pinned per project, currently Qwen3.6-35B-A3B, Qwen3.8-27B and DeepSeek V4 Flash, with context from 128k to 256k.

Because capacity rather than usage is billed, there is no usage window, no reset timer and no per-token meter, so a busy month costs the same as a quiet one. Everything runs in an EU region under Italian jurisdiction.

Three tiers from EUR 15/month (Starter) through Rise at EUR 30 to Plus at EUR 45, each scaling by concurrent-instance count.

Pricing: Monthly subscriptions

HQ 🇮🇹 Italy
Compliance GDPR
Screenshot of Solheim AI webpage

Work on Solheim AI? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →