Topic

Hosted LLM inference

Services that run large language models on a provider's own hardware and expose them to customers over an HTTP API, so callers do not manage GPUs, model weights or serving software.

Current clusters

build1 publisher

Hetzner's free inference experiment caps output at 60,000 tokens a minute

Hetzner's experimental endpoint serves one Qwen model from German and Finnish data centres at no charge, and its own documentation tells users to keep production environments off it. Future token prices have not been published.

Publishers:dev.to

Reality

Evidence40
Adoption18
Hype gap+30
Incentives60
Confidence50