Open-source model: definition

An open-source model is one whose weights are published so you can run it on your own infrastructure, giving you control over data and cost at the price of hosting it yourself.

Models like Llama, Mistral, and others can be downloaded and run on hardware you control, rather than called over an API. The trade is clear: more control over where data goes and often lower cost at scale, against the work of hosting and maintaining it.

We reach for open models when data residency or volume economics call for it, and for hosted APIs when speed of delivery matters more. It is a per-workload decision, not a loyalty.

Related terms

Large language model (LLM): A large language model is a neural network trained on huge amounts of text to predict the next token, which lets it write, summarise, classify, and answer questions across almost any topic.
Inference: Inference is the act of running a trained model to get an output, and inference cost is what you pay each time the model answers, measured in tokens.
Fine-tuning: Fine-tuning is further training a base model on your own examples so it learns a specific style, format, or task more reliably than prompting alone can achieve.