About cLLMHub
What cLLMHub is
cLLMHub is a hosted gateway for self-hosted LLMs. You run an open-weight model on your own hardware — with Ollama, vLLM, llama.cpp, MLX, LM Studio, or any OpenAI-compatible server — and we make it callable from anywhere through a stable, OpenAI-compatible API at api.cllmhub.com/v1. Streaming, tool calls, and vision all work.
What it's for
For people who want to use their own LLM hardware — a home GPU, an Apple Silicon Mac, a workstation, or a cheap cloud VM — without exposing it directly to the internet, building their own OpenAI-compatible wrapper, or maintaining their own auth and rate-limiting layer. You run the model; we run the gateway.
How pricing works
cLLMHub is a subscription for the gateway service. Free, Pro, and Max plans determine your daily request quota and the number of models and API keys you can register. See the pricing page for details. Billing is monthly via PayPal; you can cancel anytime.
Your weights stay home
The CLI opens an outbound WebSocket from your machine to the gateway — no inbound ports to forward, no model uploads. Inference runs on your hardware; the gateway just routes requests and responses. If your machine goes offline, the model returns offline; nothing leaks.
Open source
The cLLMHub CLI is open source under the Apache 2.0 license. You can inspect, audit, and contribute to the code on GitHub.