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.
Glossary
266 terms · A–Z
Definitions first, then how it works, worked examples, formulas and code.
LLM API pricing
62 models · 5 vendors
Per-token prices from each vendor's own page, with cache, batch and long-context rates.
Models
7 model cards · 6 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
20 changes · last Sep 15, 2026
Model launches, price changes and retirements, each linked to the vendor's notice.
News and research
184 articles
Pricing news, research summaries and applied machine learning explainers.
Paying for a chat app rather than the API? See chatbot subscription plans.
Recently updated in the glossary
Latest articles
PyTorch: What It Is, Its Real History, and How to Use It
PyTorch is an open-source deep learning library originally built at Facebook AI Research (now Meta AI), and since September 2022 it's governed independently by the…
Claude Code Tutorial: From First Session to Subagents and Hooks
Claude Code is Anthropic's agentic coding tool: a terminal program, IDE extension, desktop app, and web client that reads your codebase, edits files, runs commands, and…
How to Reduce LLM API Costs: A $295-to-$5.75 Worked Example
Every LLM API bill is the same equation: tokens × price per token . OpenAI's own production guidance puts it in exactly those terms — cut the number of tokens, cut the…
How to Build an AI Agent: A Working Example in 100 Lines
An AI agent is a language model that can call your code, look at what came back, and decide what to do next. That is the whole idea. Anthropic puts it plainly in…
Prompt Caching: How It Works and What It Actually Saves
Prompt caching lets a model skip work it has already done. When two requests begin with the same text — the same system prompt, the same document, the same conversation…
How to Run an LLM Locally With Ollama
Running a large language model on your own computer takes two commands. The first installs Ollama, the second downloads a model and starts a chat: