Category

The model layer: who makes what you build on

Every AI application sits on top of a model, and every model belongs to a family with its own maker, license, and access paths. These entries cover the major families - Claude, GPT, Gemini, Llama, Mistral, DeepSeek, and Qwen - plus what benchmarks really tell you and a practical framework for choosing among them. The focus is durable identity: who builds each family, whether the weights are open or closed, and how your code actually reaches the model.

Entries in this category

Where this layer fits

Models are the center of the stack, but they never work alone. Upstream, core concepts explain what these families are made of - transformers, tokens, and context windows. Downstream, the inference layer determines where a model actually runs and what it costs, and evals tell you whether the family you picked is really the right one.

Not sure where to start? Choosing a model ties this whole category together. Or browse everything at once in the A-Z index.