Glossary: models and costs
How a language model works from the inside and what decides how much you pay: tokens, context, reasoning, fine-tuning and use through an API.
6 pages, in alphabetical order. The whole glossary from A to Z
What is a token in AI, and why it decides what you pay
A token is the piece of text a language model reads and writes with: it can be a whole word, part of a word or a punctuation mark.
What a frontier model is and when you don't need to pay for one
The most powerful model on the market is often the wrong one for everyday work.
What a frontier model is, and when it's not worth paying
They are the most powerful models on the market. For many jobs in an SMB, they are also the most wasteful.
What is AI model distillation?
It is why there are models almost as good as the best ones, but much cheaper.
What is an LLM? The language model behind ChatGPT, Claude and Gemini
One word explains why so many AI tools look alike, and why you sometimes pay twice for the same thing.
What's an LLM? The model behind ChatGPT, Claude and Gemini
Almost every AI tool you are offered uses one. Often it is the same one, resold at different prices.