LlamaParse Platform icon

LlamaParse Platform

Parse, classify, split, extract structured data, and retrieve context from documents and indexes using the LlamaParse Platform

Actions6

Parse a Document

AI-generated

Summary

Parse each document with LlamaParse and return its full text or Markdown as an n8n item. Choose the input source and parsing tier; binary files are uploaded to LlamaParse before parsing, and the node waits for the parse job to finish.

Inputs

  • Tier — Quality and cost setting: Fast (default, plain text), Cost Effective (Markdown), Agentic, or Agentic Plus.
  • Version — Parse service version; defaults to latest.
  • Input Type — Choose Binary File (default), File ID, or File URL.
  • Input Data Field Name (required) — For Binary File input, the incoming item's binary property containing the document; defaults to data.
  • File ID (required) — For File ID input, the ID of a previously uploaded LlamaParse Platform file.
  • URL (required) — For File URL input, a publicly accessible URL for the document.

Output shape

One item per successfully parsed input, with JSON field text containing the parsed content.

The node returns Markdown when available, otherwise full text. Fast requests only full text; other tiers request both full text and Markdown. It uploads binary input, creates a parse job, and polls until completion; failed or cancelled jobs produce an error. With Continue On Fail enabled, errors are returned as an item with an error field.

Links

Discussion