A family of large language models from OpenAI, based on the transformer architecture and pretrained on big text collections, used to understand and produce language and code.
Also called Generative Pretrained Transformer.
Read more: Microsoft Learn
In the Ultra Transcenders books
Each book explains GPT in context, with comparison tables and the common traps.
Terms in this definition
- Transformer
The neural network design underlying GPT and most other LLMs. Text is tokenised and embedded, attention is applied across the context, and the next token is predicted.
Related terms
- Azure OpenAI
Use of OpenAI models in Azure, including GPT, o-series, embeddings, image and Whisper, through either a Foundry resource or an Azure OpenAI resource. Content Understanding isn't available from a standalone Azure OpenAI resource.
- Codex
Former OpenAI model for code (code-davinci-002), now retired in Azure; current GPT models, GPT-5 codex variants among them, do coding work instead, and codex-mini is itself deprecated with retirement on 15 November 2026.
- MBR
An older partitioning scheme tied to BIOS, allowing at most four primary partitions and disks up to 2 TB. On UEFI machines, GPT takes its place.