# What are GPT models?

> GPT models are OpenAI's family of language models behind ChatGPT and the OpenAI API. What GPT stands for, how the versions work and which one to pick.

Source: https://learn.ynteractive.com/content/glossary/gpt-models · Updated 2026-10-08 · Free from Stepthrough (https://learn.ynteractive.com)

[AI basics](https://learn.ynteractive.com/content/glossary#topic-ai-basics) · [AI glossary](https://learn.ynteractive.com/content/glossary)

Quick answer

GPT models are OpenAI's family of large language models. GPT stands for "generative pre-trained transformer": a model trained on a huge amount of text that generates new text one token at a time. Each new version, and each smaller or faster variant, gets its own name and number.

Last updated October 8, 2026

Updated October 8, 2026 · By [Robert Breen](https://learn.ynteractive.com/content/about)

## Why it matters for a small business

The name shows up in two places. In ChatGPT, you mostly don't have to choose: OpenAI's help center says that, as of October 2026, paid plans are moving to **GPT-6** while the Free and Go plans default to a GPT-5.6 model, and a **Thinking** setting decides how long the model reasons before answering. In tools that call the [OpenAI API](https://learn.ynteractive.com/content/glossary/openai-api), you do choose, from a list of named models that differ in price, speed and ability.

For a small business, the useful rule is the same one that applies to every [model family](https://learn.ynteractive.com/content/glossary/model-family): pick the smallest, cheapest model that does the job well, and move up only when it doesn't. A "mini" model costs a fraction of the flagship per token, so for sorting emails or drafting short posts it is usually the better buy. Model names change several times a year, so check OpenAI's current models page instead of trusting an old tutorial.

## In a real lesson: n8n AI Agent Tutorial: Save Social Media Ideas to Google Sheets

In the [AI Social Media Idea Agent lesson](https://learn.ynteractive.com/content/n8n-ai-agent-tutorial-google-sheets), you add the **OpenAI Chat Model** to an n8n agent and open the **Model** dropdown. The list is the GPT family, and the lesson picks **gpt-5-mini**: "Fast, cheap, and plenty for generating social media ideas."

That is the right first pick for a job like this. The agent writes three post ideas for BrightPath Marketing, a made-up agency, and saves them to a Google Sheet. Nothing about it needs the biggest model. If the ideas came back weak, you would switch the dropdown to a larger GPT model and test again, without rebuilding anything else.

[Try this lesson free](https://learn.ynteractive.com/modules/n8n-ai-agent) or [read the step-by-step guide](https://learn.ynteractive.com/content/n8n-ai-agent-tutorial-google-sheets).

## Common confusions

### GPT models vs ChatGPT

[ChatGPT](https://learn.ynteractive.com/content/glossary/chatgpt) is the app. GPT models are the engines inside it. The app adds memory, projects, files, search and settings on top of the model.

### GPT vs "a GPT"

OpenAI also used "GPTs" for custom chatbots people built in ChatGPT. Those are being retired in favor of Projects, and they are not models.

## Tips

- In automations, start with a mini model and upgrade only if the output falls short.
- Write the model name into your workflow notes so you know what to retest when it changes.
- In ChatGPT, use more thinking time for multi-step problems, not for quick drafts.

## Related terms

[OpenAI](https://learn.ynteractive.com/content/glossary/openai) · [ChatGPT](https://learn.ynteractive.com/content/glossary/chatgpt) · [OpenAI API](https://learn.ynteractive.com/content/glossary/openai-api) · [Model family](https://learn.ynteractive.com/content/glossary/model-family) · [Reasoning model](https://learn.ynteractive.com/content/glossary/reasoning-model) · [Large language model (LLM)](https://learn.ynteractive.com/content/glossary/large-language-model)

## More AI basics terms

[Grounding](https://learn.ynteractive.com/content/glossary/grounding) · [Hallucination](https://learn.ynteractive.com/content/glossary/hallucination) · [Inference](https://learn.ynteractive.com/content/glossary/inference) · [Intelligent document processing](https://learn.ynteractive.com/content/glossary/intelligent-document-processing)

## Where you use it: free lessons

- [n8n AI Agent Tutorial: Save Social Media Ideas to Google Sheets](https://learn.ynteractive.com/content/n8n-ai-agent-tutorial-google-sheets) (n8n, 12 min)
- [AI Email Responder: Draft Gmail Replies Automatically with n8n](https://learn.ynteractive.com/content/ai-email-responder-gmail-drafts-n8n) (n8n, 12 min)
- [Prompt Writing 101: Role, Context, Task, Format](https://learn.ynteractive.com/content/prompt-writing-101-role-context-task-format) (ChatGPT, 8 min)

## More free tutorials

[ChatGPT tutorials](https://learn.ynteractive.com/content/tool/chatgpt)

## Frequently asked questions

**What does GPT stand for?**

Generative pre-trained transformer. Generative means it produces text, pre-trained means it learned from a large body of text before being tuned, and transformer is the type of neural network it uses.

**Which GPT model is in ChatGPT right now?**

As of October 2026, OpenAI's help center says GPT-6 is rolling out to paid plans and the Free and Go plans default to a GPT-5.6 model. ChatGPT shows the current model in its model menu.

**Is a newer GPT model always better?**

Usually more capable, not always better for your job. A newer flagship can cost more and run slower. For simple, repeated tasks, a smaller model is often good enough and much cheaper.

[All AI glossary terms, A to Z](https://learn.ynteractive.com/content/glossary) · [Free prompt templates](https://learn.ynteractive.com/content/prompts)
