# OpenAI o-series

> Made by OpenAI. They think it through first, then answer.

**Field:** Artificial Intelligence  
**Category:** Models & Providers  
**Also known as:** o1, OpenAI o1, o1-preview, o3, o3-mini, o4-mini

## Think of it like

It is like a kid who works a sum out on paper first. Then they say the answer.

## Definition

The OpenAI o-series is a family of reasoning models made by OpenAI. Before each answer, the model writes a long chain of hidden working. Only then does it give its reply. The first one, o1-preview, came out in September 2024. Later ones include o1, o3-mini, o3 and o4-mini. They do best at maths, science and code, but cost more and reply slower than GPT models.

## Example

Jack gives o3 a hard puzzle about train times. It thinks for half a minute, then gives the right answer and its steps.

## Why it matters

It showed that more time to think, not just a bigger model, can make answers better.

## Common mistake

Thinking an o-series model is just a newer GPT. It is a separate line, built to think first, and it is slow on simple tasks.

## Three principles

- **Think first.** Hidden working, then a short answer.
- **Pay for thinking.** The working is billed as output.
- **Pick it for hard tasks.** Maths, science and code.

## Related terms

- [Reasoning Model](https://learn.benibix.com/term/ai/reasoning-model)
- [Extended Thinking](https://learn.benibix.com/term/ai/extended-thinking)
- [Test-Time Compute](https://learn.benibix.com/term/ai/test-time-compute)
- [GPT (Generative Pre-trained Transformer)](https://learn.benibix.com/term/ai/gpt)
- [OpenAI](https://learn.benibix.com/term/ai/openai)

## Told apart from

- [OpenAI o-series vs GPT](https://learn.benibix.com/compare/openai-o-series-vs-gpt): People think an o-series model is just a newer GPT, and it is not. A GPT model starts its answer straight away. An o-series model first writes out hidden working, then answers. That makes it better at maths, code and hard puzzles. It is also slower and costs more, so a GPT model is often the better pick for simple jobs.

## Taught in

- [Reasoning Models and Thinking](https://learn.benibix.com/learn/ai-llms/reasoning-models): LLMs, 12/15
- [AI Model Names and Sizes](https://learn.benibix.com/learn/ai-models-providers/ai-model-names-and-sizes): AI Models and Providers, 6/13

![Two paths from a question to an answer. The top path goes straight to an answer. The bottom path first passes through a box of thinking steps, then gives the answer.](https://learn.benibix.com/diagrams/llm-reasoning.svg)

---

Source: https://learn.benibix.com/term/ai/openai-o-series
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-19
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
