Models
One model today, served properly.
Each model gets its own card with the real numbers: pricing, context, quantization, where it runs, and performance measured on live traffic rather than quoted from a spec sheet. New models are announced in the changelog and appear in GET /v1/models the same day.
Qwen3.8-27B
unsloth/Qwen3.8-27B-NVFP4 · id in the API:
unsloth/Qwen3.8-27B-NVFP4context262,144 tokens
max output32,768 tokens
inputtext and images
quantizationNVFP4 on NVIDIA RTX PRO 6000 Blackwell
pricing$0.25 / $2.09 / $0.04 per M (input / output / cached input)
runs inHelsinki, Finland (EU), edge in Nuremberg, Germany
data handlingzero retention of request and response content
Full model card with measured performance and GDPR answers →
Programmatic list
The authoritative list is the API itself: GET https://api.llmtech.eu/v1/models needs no key and returns every model with its context length, features and per-token prices. Catalog integrations should read that endpoint rather than this page.