LlamaParse is our commercial platform designed to automate document workflows, including agentic document parsing, extraction and indexing. It provides a generous provision of 10k free credits a month to all new users, but is not open source.

Our open source projects, LlamaIndex and Workflows, provide AI builders with the foundational building blocks for creating AI apps. They include both low-level and high-level abstractions that can be deployed in just a few lines of code.

It depends on the modes or options selected.

1. Basic Parsing: as low as 1 credit

2. Layout-aware agentic parsing with LLMs or VLMs: higher credit cost for greater accuracy

LlamaParse allows you to balance cost and accuracy and tweak settings without requiring retraining like traditional document processing solutions. We recommend testing new document types with different settings before configuring persistent pipelines.

LlamaParse SaaS is hosted on a secure cloud tenant, with data encrypted in transit and at rest. Cached data is retained only for 48 hours before permanently deletion (done to avoid additional costs as you experiment with various configurations). You have the option to turn caching OFF.

For enterprises, we also offer deployment in private VPCs across all cloud providers, ensuring data never leaves your tenant. LlamaParse is available on both the AWS and Microsoft Azure marketplaces.

LlamaParse is certified for:

1. SOC 2 Type II

2. GDPR

3. HIPAA

For more details, visit our Trust Center.