Navigation

Mobile Docs

Mistral Parser

Extract text from PDF documents

Extract text and structure from PDF documents using Mistral's OCR API. Either enter a URL to a PDF document or upload a PDF file directly. Configure processing options and get the content in your preferred format. For URLs, they must be publicly accessible and point to a valid PDF file. Note: Google Drive, Dropbox, and other cloud storage links are not supported; use a direct download URL from a web server instead.

Toolsmistral_parse

Usage

01Add the block to your workflow and connect it to the upstream step.
02Configure any required credentials or tokens in the inputs.
03Fill in required inputs and optional parameters for the run.
04Run a test execution, inspect outputs, and iterate before deploying.
05Deploy the mistral_parse block with monitoring enabled in production.

Inputs (UI)

Select Input Method

dropdown

Layout: full

Options: PDF Document URL, Upload PDF Document

PDF Document URL

short-input

Placeholder: Enter full URL to a PDF document (https://example.com/document.pdf)

Layout: full

Condition: inputMethod = "url"

Upload PDF

file-upload

Layout: full

Condition: inputMethod = "upload"

Output Format

dropdown

Layout: full

Options: Markdown (Formatted), Plain Text, JSON (Raw)

Specific Pages

short-input

Placeholder: e.g. 0,1,2 (leave empty for all pages)

Layout: full

API Key

short-input

Placeholder: Enter your Mistral API key

Layout: full

Inputs (API)

inputMethod

string

Optional

filePath

string

Optional

fileUpload

json

Optional

apiKey

string

Required

resultType

string

Optional

pages

string

Optional

Outputs

Primary response type:

{
  "content": "string",
  "metadata": "json"
}

Tool Access

mistral_parser