# TOKEN SUPPLY

When you feed a prompt into the supply section, it will trigger the machine learning algorithms to interpret your instruction to determine the total supply of tokens.

For those aiming for precise control over the token supply, you can guide the ai models by framing your prompt in a directive manner, such as "69420000000."

This instructs the model to adhere strictly to your specified value, minimizing any randomness in the output.

<figure><img src="/files/1ANDDLeaUjeyZywNUmnP" alt=""><figcaption></figcaption></figure>

On the other end of the spectrum, the ai model can creatively surprise you with very creative numbers.

By loosening the "temperature" setting and formulating a more open-ended prompt, you can receive suggestions as intricate as mathematical constants like π for your token's total supply.

<figure><img src="/files/dzCkY0pSrkA1uczpzOOE" alt=""><figcaption></figcaption></figure>

Thus, whether you prefer a deterministic supply number or wish to venture into more creative numerical territories, the system offers the flexibility to cater to both ends of the spectrum.

If you know exactly what you want for supply, you can also directly write the response wanted without the use of ai. (toggle the ai switch off)

<figure><img src="/files/cQgrDOwLLtsId9Vfke1n" alt=""><figcaption></figcaption></figure>

NOTE: ALL SOLANA TOKENS, REGARDLESS OF GENERATED SUPPLY WILL HAVE 1,000,000,000 TOKENS TO ADHERE TO BONDING CURVE REQUIREMENTS.


---

# 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.aiis.dev/creating-generations/token-supply.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.