Run models on sovereign EU infrastructure.
Sub-50ms latency. OpenAI-compatible API.
curl https://api.icebase.ai/v1/chat/completions \ -H "Authorization: Bearer $ICEBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "meta-llama/llama-3.1-70b", "messages": [{"role": "user", "content": "Hello"}], "stream": true }'
Purpose-built for teams that need European AI infrastructure without compromise.
All processing on European infrastructure. Your data stays in the EU.
Edge-optimized routing across major European metros.
Built with European data protection requirements in mind.
OpenAI-compatible API. Switch in minutes, not weeks.
Standard endpoints. Bring your own stack.
Designed for uptime-critical workloads from day one.
Open-weight models optimized for European inference. OpenAI-compatible API.
Real-time response times from our European edge nodes. Routed from Iceland through Frankfurt, London, Amsterdam, Paris, and Stockholm.
Measured from nearest edge node. Actual latency may vary.
No minimums. No commitments. Pay only for what you use.
From €0.05 / 1M tokens