> ## Documentation Index
> Fetch the complete documentation index at: https://docs.landing.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Credit Consumption

> Understand credit consumption for the ADE v2 Parse and Extract APIs.

export const ade = 'Agentic Document Extraction';

This page covers credit consumption for the {ade} v2 APIs. For plan and billing details and pricing for other ADE tools, see [Plans & Billing](../ade/ade-pricing).

All credit totals are rounded up to the nearest 0.1 credit.

## Parse

The Parse v2 API uses complexity-aware pricing: each page's credit consumption scales with the volume of content returned, so simpler pages consume fewer credits and denser pages consume more.

Each page's credit consumption is the sum of the two components below.

Output characters are the characters in the returned `markdown` field, excluding the page-break and document-ID markers.

| Component         | Credit Consumption                      |
| :---------------- | :-------------------------------------- |
| Page              | 1 credit per page                       |
| Output characters | 0.5 credits per 1,000 output characters |

## Parse Jobs

[Parse Jobs v2](./parse-async) uses the same complexity-aware per-page pricing as the Parse v2 API, with a service tier that sets the rate.

Choose the tier with the `service_tier` field when you create a job; if you omit it, the job runs on the `standard` tier.

The `standard` tier consumes half as many credits as the `priority` tier. The `priority` tier consumes credits at the same rate as the synchronous Parse v2 API.

| Component         | Priority                                | Standard (default)                       |
| :---------------- | :-------------------------------------- | :--------------------------------------- |
| Page              | 1 credit per page                       | 0.5 credits per page                     |
| Output characters | 0.5 credits per 1,000 output characters | 0.25 credits per 1,000 output characters |

<Info>
  For how to set the tier, see [Parse Asynchronously](./parse-async#choose-a-service-tier).
</Info>

## Extract

The Extract v2 API consumes credits based on the number of input and output characters.

Input characters are the Markdown you send.

Output characters are the characters in the returned `extraction` and `extraction_metadata` fields, excluding indentation whitespace.

| Component         | Credit Consumption            |
| :---------------- | :---------------------------- |
| Input characters  | 1 credit per 2,500 characters |
| Output characters | 1 credit per 500 characters   |

## Extract Jobs

[Extract Jobs v2](./extract-async) uses the same character-based pricing as the Extract v2 API, with a service tier that sets the rate.

Choose the tier with the `service_tier` field when you create a job; if you omit it, the job runs on the `standard` tier.

The `standard` tier consumes half as many credits as the `priority` tier. The `priority` tier consumes credits at the same rate as the synchronous Extract v2 API.

| Component         | Priority                      | Standard (default)            |
| :---------------- | :---------------------------- | :---------------------------- |
| Input characters  | 1 credit per 2,500 characters | 1 credit per 5,000 characters |
| Output characters | 1 credit per 500 characters   | 1 credit per 1,000 characters |

<Info>
  For how to set the tier, see [Extract Asynchronously](./extract-async#choose-a-service-tier).
</Info>

## Zero Data Retention

Using [Zero Data Retention](../ade/zdr) (ZDR) with the ADE v2 APIs does not consume any additional credits.