Modelship

Self-hosted, OpenAI-compatible inference server sharing GPUs across many models through one gateway.

Servicefree

Modelship is a self-hosted, OpenAI-compatible inference server built on Ray Serve, serving reasoning LLMs, universal tool calling, embeddings, speech and image models from one gateway while sharing GPU capacity across them. It's aimed at teams running multiple AI models who want a single self-hosted inference layer instead of separate stacks per model type.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Modelship - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Modelship to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Modelship (or something else) actually fits.

Try a problem