# What are the tokens of an AI model?

Imagine you have an artificial intelligence model like a virtual assistant. "Tokens" are like the basic building blocks with which this assistant constructs its responses.

In simple terms, when you type a sentence or a question and send it to the AI model, the model breaks that sentence down into small parts, called tokens. These tokens are basically individual words or parts of words that the model can understand and analyze to provide an appropriate response.

For example, if you ask your virtual assistant "What is the capital of France?", the model will divide this sentence into tokens like "What", "is", "the", "capital", "of", and "France". Each token has a specific meaning and helps the model understand the question and generate an accurate response.

In short, tokens are like puzzle pieces that the model uses to understand and respond to the questions or instructions given to it.

{% hint style="danger" %}
Attention, these tokens are not connected to $MDAI, they simply serve to fuel the AI model.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.mindaiproject.com/utility/mindai-chatbot/what-are-the-tokens-of-an-ai-model.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.