# Word credits and usage

Source: https://iachecker.com/docs/credits-and-usage
Status: Available now
Last verified: 2026-08-08

IA Checker currently meters eligible server-side writing operations in input-word credits, not model tokens. The calculation is transparent and shared across the paid writing tools.

## Credit formula

**Current web-product calculation**

```text
credits = ceil(input_words × tool_multiplier)
```

*Current writing multipliers*

| Operation | Multiplier | Example for 500 words |
| --- | --- | --- |
| Advanced Humanizer | 1× | 500 credits |
| Maximum Humanizer | 3× | 1,500 credits |
| Paraphrase, grammar, translate, summarize | 1× | 500 credits |

## What does not use word credits

- Local pasted-text detection
- URL scanning
- Document extraction by itself
- Image detection jobs

Access rules can still apply even when a workflow does not debit the shared word pool. For example, document upload requires Plus and image analysis requires Pro or Max.

## Monthly reset and plan units

Usage is calculated for the current UTC calendar month and resets on the first day of the next UTC month. Max can scale its monthly credit pool through one to four credit units while keeping the same per-check character cap.

> **Words are not model tokens**
>
> The current counter splits input on whitespace. A future public API will need a versioned billable-unit definition, especially for languages that do not separate words with spaces.

## Documentation index

- [IA Checker documentation](https://iachecker.com/docs)
- [Assistant index](https://iachecker.com/llms.txt)
- [Privacy Policy](https://iachecker.com/privacy)