OCRRouter

LlamaParse vs Chunkr

Pick LlamaParse for hosted RAG ingestion of mixed PDF and office files, where you want a free tier and a per-page price you can tune by mode. Pick Chunkr if you need to self-host layout parsing or want bounding boxes and HTML output. The main split is deployment: LlamaParse is hosted only and proprietary, while Chunkr also ships under AGPL-3.0.

LlamaParsellamaindex/llamaparseChunkrchunkr/chunkr
TypeOCR APIOCR API
Price5 credits / page14 credits / page
Per 1,000 pages$5.00$14.00
Typical speed3.0 s / page3.0 s / page
Best forRAG ingestionLayout-aware chunks for RAG
InputsPDF, images, DOCXPDF, images, DOCX
Languages80+ languagesMultilingual
Max pages per request1,0001,000
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNoNo
Multilingual✓ Yes✓ Yes
On OCRRouterAvailableAvailable

Prices are what you pay on OCRRouter. Speed is the provider's typical figure, not a benchmark we ran.

Which to choose

Choose LlamaParse if

  • You want a hosted API with 10,000 free credits per month and no servers to run.
  • You can pick a tier per job, from Fast at 1 credit per page up to Agentic Plus at 45 credits per page.
  • You re-parse the same files often, since a repeat parse within 48 hours is free because results are cached.

Choose Chunkr if

  • You need to run it yourself via Docker, with GPU, CPU-only and Mac ARM options.
  • You want HTML output and OCR with bounding boxes as well as Markdown and JSON.
  • You already have an OpenAI-compatible LLM endpoint and want to plug it in.

Key differences

LlamaParseChunkr
How you run itHosted API onlyCloud API or self-host with Docker
LicenceProprietaryAGPL-3.0 or commercial license; closed-source use needs the commercial license
Price$1.25 per 1,000 credits; about $1.25 to $56 per 1,000 pages depending on mode; 10K free credits per monthHosted credit-based plans, official prices not verified; open-source version is free but you pay for compute and an LLM endpoint
Output formatsMarkdown, JSON, plain text, imagesHTML, Markdown, JSON, bounding boxes
Input filesPDFs and office filesPDF, PPT, Word and images; Excel not supported in the open-source version
BenchmarksNot publishedNot published
Known failureReported invented transactions on bank statements and hallucination on low-quality scans with no confidence score; one job stuck in progress for daysOpen-source version uses community models that are less accurate than the cloud's in-house models

Sources

What each one is

LlamaParse

Document parser built for RAG pipelines, with several quality tiers.

LlamaParse details

Chunkr

Document parsing API that segments and chunks pages for RAG. Self-hostable version available.

Chunkr details

Try both on your own file

Run the file once with each model and compare the output.

PDF, PNG, JPG, WebP, HEIC. Up to 20 MB each, 10 files.No file?

Use one, fall back to the other

{"model": "llamaindex/llamaparse","fallbacks": ["chunkr/chunkr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

LlamaParse alternativesChunkr alternativesBest OCR models in 2026