Heabsy AI Inference is an OpenAI- and Anthropic-compatible inference API from an EU company. The flagship model runs on dedicated GPUs in EEA data centres with zero data retention: prompts and completions are processed in memory only, not stored, not logged, not used for training. Routed open models from third-party providers are available with the same key and clearly labelled in the catalog. One DPA and one invoice from an EU company.
It is built for companies that need LLM inference under EU data-protection requirements and for developers of AI agents and RAG applications. Existing OpenAI or Anthropic SDKs, Claude Code and Cursor work by changing the base URL.
Heabsy AI Inference is operated by FEYA, s.r.o. from Bratislava, Slovakia. Platform: https://heabsy.com/platform · Models and pricing: https://heabsy.com/models · DPA: https://heabsy.com/dpa
