OCRRouter

LlamaParse vs Chandra

Pick Chandra if you need multilingual scans, tables, forms or math, or want to self-host on your own GPU. Pick LlamaParse if you want a hosted API for mixed PDF and office files inside a LlamaIndex RAG pipeline and prefer to pay per page with a free monthly allowance. Validate LlamaParse output on bank statements and poor scans, and validate Chandra output on old or low-resource-script scans.

LlamaParsellamaindex/llamaparseChandradatalab/chandra
TypeOCR APIOpen source
Price5 credits / page2 credits / page
Per 1,000 pages$5.00$2.00
Typical speed3.0 s / page2.0 s / page
Best forRAG ingestionComplex layouts and handwriting
InputsPDF, images, DOCXPDF, images
Languages80+ languages40+ languages
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNo✓ Yes
Math✓ Yes✓ Yes
Bounding boxes✓ Yes✓ Yes
ConfidenceNoNo
FormsNo✓ Yes
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

  • It handles PDFs and office files in one hosted service, so you do not run any model yourself.
  • It fits RAG ingestion inside LlamaIndex pipelines, and re-parsing the same file within 48 hours is free because results are cached.
  • It has a wide price range, from $1.25 per 1,000 pages in Fast mode to agentic modes for hard layouts, with 10,000 free credits per month.

Choose Chandra if

  • You can self-host the open weights on a single NVIDIA GPU with vLLM, or use the hosted Datalab API if you prefer.
  • It scores 85.8 on olmOCR-bench and 77.8% averaged across 43 languages, so it suits multilingual scanned documents.
  • It returns Markdown, HTML and JSON with bounding boxes and labels per block, which helps with tables, forms and math.

Key differences

LlamaParseChandra
How you run itHosted API onlySelf-host the open weights (vLLM or Hugging Face) or use the hosted Datalab API
LicenceProprietaryCode Apache-2.0; weights modified OpenRAIL-M, free for research, personal use and companies under $2M funding/revenue
Price$1.25 per 1,000 credits. Fast 1 credit/page, Cost Effective 3, Agentic 10, Agentic Plus 45. 10K free credits per monthSelf-hosted: free within license terms, you pay for compute. Datalab API: $1, $3 or $7.50 per 1,000 pages; $20/month free tier with a work email
Output formatsMarkdown, JSON, plain text, imagesMarkdown, HTML, JSON, bounding boxes
BenchmarkNot publishedolmOCR-bench 85.8 overall (Chandra 2, authors' figure)
Known failureInvented transactions on bank statements in Accurate mode; hallucinations on low-quality scans with no confidence score or errorToken-loop hallucinations on some Russian/Kazakh scans; weak on Urdu (43.2%), Sanskrit (51.1%) and old scans (51.1 on olmOCR-bench)
SpeedPremium mode took 4 to 5 minutes in one report; one job stuck for daysAbout 1.44 pages/s on one H100 with vLLM; one reviewer measured 66 seconds per page on an RTX 4090 with the Hugging Face path

Sources

What each one is

LlamaParse

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

LlamaParse details

Chandra

Datalab's OCR model that keeps layout and handles forms, tables and handwriting.

Chandra 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": ["datalab/chandra"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

LlamaParse alternativesChandra alternativesBest OCR models in 2026