Inference Embeddings Rerank Images Speech Guard
DE ES IT

Sovereign AI Inference,
built for Europe.

German HQ 100% EU data residency

Open-source models on European GPUs.
GDPR by design. Powered by Nordic green energy.
Your data never leaves the EU.

Create free account 100K tokens/month free
// models + pricing

Our Models

We run the best-performing open-source model families for reasoning, coding and multilingual tasks. Fully open weights, no black box. Combined with European hosting, you get frontier-level quality without sending a single token overseas.

All models run on modern Blackwell or newer chips for ideal performance. Pricing per million tokens. Free tier included on all models.

Qwen Qwen
Dense
5690
Qwen3.5 9B
Input: 0,20 € · Output: 0,30 € Coming soon
Qwen3.5 9B
56
GPT-5 Nano
47
Haiku 4.5
65
Gemini 3.1 FL
60
Mistral Small 3.2
26
7470
Qwen3.5 27B
Input: 0,40 € · Output: 3,00 €
Qwen3.5 27B
74
GPT-5 Mini
72
Sonnet 4.5
75
Gemini 3 Fl.
61
Mistral Medium 3.1
37
Mixture of Experts
6592
Qwen3.5 35B-A3B
Input: 0,30 € · Output: 2,50 €
Qwen3.5 35B-A3B
65
GPT-5 Nano
47
Haiku 4.5
65
Gemini 3.1 FL
60
Mistral Small 3.2
26
7778
Qwen3.5 122B-A10B
Input: 0,50 € · Output: 4,00 €
Qwen3.5 122B-A10B
77
GPT-5 Mini
72
Sonnet 4.5
75
Gemini 3 Fl.
61
Mistral Medium 3.1
37
7960
Qwen3.5 397B-A17B
Input: 0,80 € · Output: 5,00 €
Qwen3.5 397B-A17B
79
GPT-5.2
89
Opus 4.5
88
Gemini 3 Pro
84
Mistral Large 3
40
Free tier
100K tokens/month All models 10 req/min No credit card
// for teams that need more

Business Plan

Predictable costs, priority capacity and guaranteed availability. One plan for all Nodion.ai products. No surprise invoices.

Business
500 € /month
Managed AI Infrastructure for Businesses
  • All products: Inference, Embeddings, and future APIs
  • 50M tokens/month included
  • Dedicated GPU capacity, priority routing
  • Model LTS - 12-month availability guarantee
  • Access all models, be the first to try out new models
  • 99.5% uptime SLA
  • Dedicated support + onboarding
Get started
// getting started

API Documentation

Nodion.ai is fully compatible with the OpenAI API. Point any OpenAI SDK or tool at our base URL and you're ready to go.

# Base URL
https://api.nodion.ai/v1
# Example: curl
curl https://api.nodion.ai/v1/chat/completions \
  -H "Authorization: Bearer $NODION_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3.5-35b-a3b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Supports: /v1/chat/completions, /v1/models. Streaming, tool use, and JSON mode included.

// why this matters
GDPR-native. Not a policy checkbox, it's how the infrastructure is built. No data leaves the EU. No transatlantic transfers. No adequacy decision risks.
Nordic green energy. GPU clusters in Sweden and Finland run on renewable energy. Cold climate means natural cooling, lower energy waste, smaller footprint.
No US dependency. German company. EU servers. Open-source models. Full stack sovereignty without hyperscaler lock-in.
Open-source only. Every model we serve is fully open. You can inspect the weights, understand the architecture, audit the outputs.
OpenAI-compatible API. Drop-in replacement. Change your base URL and you're running on sovereign European infrastructure.

Ready to start?

100K free tokens per month. No credit card required. All models included.

Create free account