> For the complete documentation index, see [/llms.txt](/llms.txt).

# Information Extract

> Source: /docs/models/information-extract

Earlier versions, including deprecated ones, are listed in [All models](/docs/models/history#information-extract).

Extract structured key data from unstructured text

[Compare](/docs/models/compare/document-intelligence) · [Try in Studio](https://studio.upstage.ai/library?lang=ko%2Cen&steps=parse%2Cextract&utm_medium=console&utm_source=docs)

- **Max pages per request**: 100 pages (up to 1000 with async API)
- **Supported character sets**: A · 가 · あ · ア · 漢
- **Outputs**: Key-values (JSON)
- **Price**: $0.04/page (Standard)
- **Price**: $0.06/page (Enhanced)

Process and extract key information from any random document without additional training or customization

- Schema-agnostic processing
- Extracts hidden and implied information
- No fine-tuning required
- Processes 1,000 pages via Async API

## Supported file formats

- JPEG: Supported
- PNG: Supported
- BMP: Supported
- TIFF: Supported
- HEIC: Supported
- PDF: Supported
- DOCX: Supported
- PPTX: Supported
- XLSX: Supported
- HWP: Supported
- HWPX: Supported

## Maximum file size

50MB

## Maximum number of pages per file

Synchronous API: **100 pages** (For files exceeding 100 pages, the first 100 pages are processed)

Asynchronous API: **1000 pages**

## Maximum pixels per page

**200,000,000 pixels**

(For non-image files, the pixel count is determined after converting to images at a standard of 150 DPI.)

## Supported character sets (if using OCR)

- Alphanumeric: Input and output
- Hangul: Input and output
- Hiragana: Input and output
- Katakana: Input and output
- Hanja: Input and output
- Hanzi (Beta): Not fully supported
- Kanji (Beta): Not fully supported

Hanja, Hanzi, and Kanji are writing systems based on Chinese characters used in Korean, Chinese, and Japanese writing systems. Despite sharing similarities, they possess distinct visual representations, pronunciations, meanings, and usage conventions within their respective linguistic contexts. For more information, see [this article](https://en.wikipedia.org/wiki/Hanja).

## Available Platforms

- Upstage Console
- [AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-426kewtegr6mo?sr=0-9&ref_=beagle&applicationId=AWSMPContessa)
- [Azure Marketplace](https://azuremarketplace.microsoft.com/en-us/marketplace/apps/upstage-marketplace.information-extract?tab=Overview)
- [On-premises](https://www.upstage.ai/contact-us?utm_medium=console&utm_source=docs-models&utm_content=text-link)

## Versions

### information-extract-260904 (Alias: information-extract)

Released on 2026-09-04

- Available platforms: Upstage Console

## API privacy

Data not collected

Upstage does not collect any data from this API

1. API input data is not used for model training.
2. API input data is not stored, unless required for service delivery and explicitly stated.

Extract Key Information in Upstage Studio!

Identify and structure critical data from unstructured documents — ideal for automation beyond basic parsing.

[Try it in Upstage Studio](https://studio.upstage.ai/library?lang=ko%2Cen&steps=parse%2Cextract&utm_medium=console&utm_source=docs)