LlamaParse

API

Document parsing API from LlamaIndex that turns PDFs and scans into markdown

Price: Free tier, then paid
Access: LlamaCloud API key

About

LlamaIndex's hosted platform for getting data out of documents: Parse turns PDFs, scans, Office files and 130+ formats into markdown or JSON, and Extract, Classify and Split work on the same key. Billed in credits per page; the Agentic tier costs 10 credits a page.

What you can do with it

Parse PDFs with tables, charts and scans into clean markdown for RAG pipelines
Extract JSON in your schema from contracts, filings and forms
Classify and split mixed document packets before extraction

Get started

Sign up at cloud.llamaindex.ai and create an API key
Upload the file to get a file_id, then start a parse job
Poll GET /api/v2/parse/<job_id>?expand=markdown for the result

Example

curl -X POST https://api.cloud.llamaindex.ai/api/v1/beta/files \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  -F 'purpose=parse' \
  -F 'file=@document.pdf;type=application/pdf'

curl -X POST https://api.cloud.llamaindex.ai/api/v2/parse \
  -H "Authorization: Bearer $LLAMA_CLOUD_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{"file_id": "<file_id>", "tier": "agentic", "version": "latest"}'

Details

Hosting: Hosted service, Self-hosted
Available in: Worldwide
Official SDKs: Python, JavaScript/TypeScript, Go, Java
MCP server: Remote