LlamaParse API
Document parser built for RAG pipelines, with several quality tiers.
- Model ID
- llamaindex/llamaparse
- Type
- OCR API
- Price
- 5 credits / page ($5.00 per 1,000 pages)
- Typical speed
- 3.0 s / page
- Inputs
- PDF, images, DOCX
- Languages
- 80+ languages
- Max pages per request
- 1,000
- Output
- Markdown, JSON with positions
- Supports
- TablesMathBounding boxesMultilingual
curl https://api.ocrrouter.ai/v1/ocr \
-H "Authorization: Bearer $OCRROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llamaindex/llamaparse",
"file_url": "https://example.com/invoice.pdf",
"format": "markdown"
}'LlamaParse is not connected yet. The price below is an estimate. You can call the models that are live today with the same request.
LlamaParse speed and reliability
Loading…
Measured on our own traffic over the last 7 days.
LlamaParse pricing
LlamaParse costs 5 credits per page. One dollar buys 1,000 credits, so 1,000 pages cost $5.00. You only pay for pages that return a result.
New accounts get 200 free credits, enough for about 40 pages with this model. See pricing for credit packs.
Similar models
1Mistral OCRFast document OCR that returns clean Markdown with tables and embedded images.
mistral/mistral-ocr6 credits / page2MarkerHosted version of the open-source Marker and Surya models. Strong on books and papers.datalab/marker14 credits / page3ChunkrDocument parsing API that segments and chunks pages for RAG. Self-hostable version available.chunkr/chunkr14 credits / pageCompare LlamaParse
LlamaParse vs Mistral OCRLlamaParse vs MarkerLlamaParse vs ChunkrLlamaParse vs KrakenLlamaParse vs Jina OCRLlamaParse vs DeepSeek-OCR