ChatGPT Glossary: AI & ChatGPT Terms Defined

ChatGPT is a conversational AI chatbot created by OpenAI, launched in November 2022. It uses large language models (current models include GPT-5.5, GPT-5.5 pro, GPT-5.4, GPT-5.4 pro, GPT-5.4 mini, GPT-5.4 nano, GPT-5 mini, GPT-5 nano, GPT-5, GPT-4.1) to understand and generate human-like text responses. It is available as a free web app at chatgpt.com with optional paid plans.

A token is the basic unit of text that ChatGPT processes. One token equals roughly 4 English characters or 0.75 words. Current ChatGPT models like GPT-5.5 and GPT-5.4 support a 1 million token context window, meaning they can process approximately 750,000 words in a single conversation.

OpenAI offers GPT-5.5, GPT-5.5 pro, GPT-5.4, GPT-5.4 pro, GPT-5.4 mini, GPT-5.4 nano, GPT-5 mini, GPT-5 nano, GPT-5, GPT-4.1. Older models (GPT-4o, o3, o4-mini, and earlier) were retired on February 13, 2026 and replaced by the GPT-5.x family.

AI Toolbox (formerly ChatGPT Toolbox) is a Chrome extension with 25,000+ active users and a 4.5/5 Chrome Web Store rating. It adds folders, advanced search, bulk export, prompt library, and prompt chaining to ChatGPT, with sibling modules covering Gemini and Claude. Available on all Chromium browsers with a free starter plan.

Prompt engineering is the practice of crafting effective text inputs to get better responses from AI models like ChatGPT. Techniques include setting a role, providing examples, requesting specific formats, and using chain-of-thought instructions.