# `TokenCount`

How many tokens a prompt or an answer holds, by its model's own count.

Use it to count one side of a model call. For a whole call's use, use [`TokenUsage`](/docs/types/type-token-usage.md).

## Shape

One whole number from 0 to 9007199254740991.

## Example

```jadpo
TokenCount(350)
```

`TokenCount(number)` checks the number, and one outside its limits breaks `min` or `max`.

`text.parse(raw, as: TokenCount)` reads one from text that comes from outside. Text that isn't one at all fails `malformed`, such as `-1`, `1.5` or `1,200`.

## Good to know

- It is a whole number from 0. In JSON it is a plain number.
- `==` tells you whether two are the same, and `<` and `list.sort_by` compare and sort them.

## In JSON

A number, in a request, a response or `json.write`:

```json
0
350
128000
```

## Details

<details>
<summary>Text form, storage, how it is shown, and operations</summary>

`TokenCount` is in the group AI, and has been in Jadpo since 0.1.0.

### Text form

`text.from` writes one standard text form, the same form `text.parse` reads back: `0`, `350` and `128000`.

### How it is stored

It is stored in one column named for the field, of type `bigint`. `350` is stored as `350`.

### How it is shown to people

`text.format(value, locale:)` shows it to people in their locale.

With `locale: Locale.en_gb`:

| Value | Shown |
|---|---|
| `0` | `0` |
| `350` | `350` |
| `128000` | `128,000` |

### Operations

It also takes `text.parse`, `text.from`, `text.format`, `json.read`, `json.write` and `==`. [How every standard type behaves](/docs/every-standard-type-meets-one-contract.md) says how they work.

</details>