AI reference

Clear AI definitions and model data you can check.

A glossary written for practitioners, research summaries, and language models compared on price, limits and capabilities, with a source and a date next to every number.

254glossary terms
142articles
75models priced
next-token-prediction.py

Glossary

254 terms · A–Z

Definitions first, then how it works, worked examples, formulas and code.

LLM API pricing

75 models · 5 vendors

Per-token prices from each vendor's own page, with cache, batch and long-context rates.

Models

21 model cards · 15 comparisons

Context windows, limits and capabilities, with the source behind each value.

Tools

Token counter · cost calculator

Count the tokens in your prompt, then see what a month of traffic costs on every model.

LLM changelog

37 changes · last Nov 18, 2026

Model launches, price changes and retirements, each linked to the vendor's notice.

News and research

142 articles

Pricing news, research summaries and applied machine learning explainers.

Paying for a chat app rather than the API? See chatbot subscription plans.

Fresh in the reference

Recently updated in the glossary

Latest articles

All 142 articles
Latest
AI in business

AI Water and Energy Use: How Much Does a ChatGPT Prompt Really Use?

A typical text prompt to ChatGPT or Gemini uses about 0.3 watt-hours of electricity and, by the companies' own figures, about a third of a millilitre of cooling water: roughly five drops. That is far less than the "bottle of water per…