# Reasoning model

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: reasoning, reasoning models, thinking model, extended thinking, thinking mode, reasoning tokens, thinking

A model, or a mode of a model, that works through a problem in intermediate steps before it answers. The extra thinking takes more time and uses more [tokens](https://ecosystem.samcarlton.com/token), and those tokens are billed.

**For example:** A [founder](https://ecosystem.samcarlton.com/founder) asks for a pricing analysis across three plans. With reasoning turned on, the model takes longer and its answer costs more [tokens](https://ecosystem.samcarlton.com/token) than a quick reply.

## Connects to (6)

- [Model](https://ecosystem.samcarlton.com/model): The trained system at the center of an AI product.
- [Token](https://ecosystem.samcarlton.com/token): In AI, a small chunk of text, roughly a word or a piece of a word, that an LLM reads and writes.
- [Inference](https://ecosystem.samcarlton.com/inference): An AI model producing an answer to a request.
- [Usage-based pricing](https://ecosystem.samcarlton.com/usage-based-pricing): A way to charge where the bill follows how much the customer uses, instead of a flat fee.
- [Output tokens](https://ecosystem.samcarlton.com/output-tokens): The tokens the model writes back.
- [Effort](https://ecosystem.samcarlton.com/effort): A setting that tells a reasoning model how much thinking to do before it answers.

Map view: https://ecosystem.samcarlton.com/reasoning-model