---
title: "Parse Document"
method: POST
path: "/v1/parse"
tags: ["Parse"]
---

# Parse Document

`POST /v1/parse`

Parse a document using OCR.

This endpoint extracts text from uploaded documents (PDF, images, Office files, etc.)
using advanced OCR technology.

**Providers:**
- `mistral`: Mistral OCR (fast, accurate, supports markdown)
- `gemini`: Google Gemini Vision (slower, very accurate)

**Features:**
- Automatic provider fallback if primary fails
- Page-level text extraction
- Markdown-formatted output
- Support for 30+ file types

**Example:**
```bash
curl -X POST https://api.chonkie.ai/v1/parse \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "file=@document.pdf" \
  -F "provider=mistral" \
  -F "return_pages=true"
```

## Query parameters

- `provider` 'mistral' | 'gemini' — OCR provider to use
- `fallback` boolean — Whether to fallback to other providers on failure
- `return_pages` boolean — Whether to return page-level information

## Headers

- `authorization` string, nullable

## Response `200`

Successful Response

- ParseResponse — Response from parsing a document.
  - `text` string, required — Full extracted text
  - `pages` PageInfo[], nullable — Page-level information
    - `text` string, required — Extracted text from the page
    - `startIndex` integer, required — Start index in full text
    - `endIndex` integer, required — End index in full text
    - `pageNumber` integer, nullable — Page number
  - `metadata` ParseMetadata, required — Metadata about the parsing operation.
    - `provider` string, required — OCR provider used
    - `pageCount` integer, nullable — Number of pages
    - `characterCount` integer, required — Total character count
    - `durationMs` number, required — Processing duration in milliseconds

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.dev/chonkie/apis/chonkie-api.md) · [All operations](https://skmtc.dev/chonkie/apis/chonkie-api/llms.txt) · [OpenAPI document](https://skmtc.dev/chonkie/apis/chonkie-api/revisions/f40f036f941c?raw)