Presets

LlamaParse supports different parsing modes to adapt to your use case. The three main parsing modes—what we refer to as Presets—are:

Fast

For simple, text-only documents

Overview

Fast Mode is perfect for documents that are mostly text, like simple PDFs or plain reports. It’s the quickest way to extract content when formatting doesn’t matter.

Under the Hood

Fast Mode skips all computationally intensive post-processing steps—no OCR, no layout reconstruction, no image extraction, and no table or heading detection. It directly returns raw text for each page.

To use Fast Mode, set fast_mode to True.

Python

parser = LlamaParse(
    fast_mode=True
)

API

curl -X 'POST' \
    'https://api.cloud.llamaindex.ai/api/parsing/upload'  \
    -H 'accept: application/json' \
    -H 'Content-Type: multipart/form-data' \
    -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
    --form 'fast_mode="true"' \
    -F 'file=@/path/to/your/file.pdf;type=application/pdf'

Balanced

Best for documents with tables and images

Overview

Balanced Mode is great for everyday documents that include a mix of images, tables, and text. You get reliable formatting without any extra setup.

Under the Hood

Balanced Mode performs OCR, image extraction, and identifies structural elements like tables and headings. This makes it well-suited for documents that require both content and context.

This is the default mode—no need to set anything explicitly in the API or SDK.

Premium

For complex documents with tables, images, and diagrams

Overview

Premium Mode is designed for complex, highly formatted documents—things like scanned financial reports, research papers, or anything with charts, tables, and diagrams. It gives you the most accurate and structured results.

Under the Hood

Premium Mode performs OCR, image extraction, and identifies structural elements such as tables and headings. It also outputs equations in LaTeX format and converts diagrams into Mermaid syntax for further analysis and visualization.

To use Premium Mode, set premium_mode to True.

Python

parser = LlamaParse(
  premium_mode=True
)

API

curl -X 'POST' \
  'https://api.cloud.llamaindex.ai/api/parsing/upload'  \
  -H 'accept: application/json' \
  -H 'Content-Type: multipart/form-data' \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  --form 'premium_mode="true"' \
  -F 'file=@/path/to/your/file.pdf;type=application/pdf'

---

Use Case Specific Presets

We also offer additional presets tailored to specific use cases.

Complex Table Mode

For complex tables. Our best mode to parse documents with complex tables. Set preset="complexTables" on API.