How it works

Go from a local model to a production API in under a minute.

Point at your model

Run Ollama, vLLM, llama.cpp, or MLX locally — on one machine or many. Any backend that speaks the OpenAI chat completions format works.

Run cllmhub publish. The CLI discovers your models and makes them available as a live API endpoint.

Create API keys, invite your team into Hives to pool models across accounts, and track every request from the dashboard.