Heabsy
EU inference API on its own GPUs in the EEA, with zero data retention and OpenAI- and Anthropic-compatible endpoints.
Heabsy is a Slovak inference API (FEYA, s.r.o.) that serves Qwen3.8 27B and its variants on GPUs it runs inside the EEA, with prompts and completions never logged. It is OpenAI- and Anthropic-compatible, so Claude Code and Cursor can point at it, and reports fresh, cached and output tokens per request.
The flagship costs $1.00 per 1M input tokens, $0.0761 cached and $3.00 output. Partner-hosted models, Claude and GPT among them, sit behind the same key and EU invoice without zero data retention, and the catalog marks them.
Pricing: Per token usage
Choosing an inference API right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Choosing an inference API right now?
One click, anonymous. Helps us know our visitors.
Thanks, that helps.
Heabsy prices by model
Per 1M tokens, read off Heabsy's own pricing page on the date shown.
| Model | Input / 1M | Cached / 1M | Output / 1M | Checked | Notes |
|---|---|---|---|---|---|
| Clef | $0.20 | – | $0.00 | 19 Oct 2026 | Served in the EEA, requests not stored. Output tokens are free; API access on request. |
| GLM 5.3 Flash | $0.20 | $0.0375 | $0.60 | 19 Oct 2026 | Partner-hosted through NanoGPT; no zero data retention, compute may run outside the EEA |
| Qwen3.8 27B | $1.00 | $0.0761 | $3.00 | 19 Oct 2026 | Own GPUs in the EEA, zero data retention; NVFP4 with MTP speculative decoding |
Heabsy Alternatives
Explore 149 products in the Inference APIs category. View all Heabsy alternatives.
DeepInfra
Run the top AI models using a simple API, pay per use. Low cost, scalable and production ready infrastructure.
LibertAI
Decentralized, privacy-first inference API running open-source LLMs in trusted execution environments
Clef
Cloudflare's open decision models: typed choices, scores and yes/no answers with probabilities, hosted or self-run.
Is your product missing?