OCRRouter

LlamaParse vs Typhoon OCR

Pick Typhoon OCR for Thai and Thai-English documents such as government forms, financial reports and books, especially if you want to self-host under Apache-2.0. Pick LlamaParse for mixed PDF and office files going into a RAG pipeline, where a hosted API with a free monthly allowance is the main draw. Neither should be trusted unchecked on structured fields: LlamaParse has invented bank statement transactions, and Typhoon OCR scores 21.0 on key-information extraction.

LlamaParsellamaindex/llamaparseTyphoon OCRtyphoon/typhoon-ocr
TypeOCR APIOpen source
Price5 credits / page2 credits / page
Per 1,000 pages$5.00$2.00
Typical speed3.0 s / page1.8 s / page
Best forRAG ingestionThai documents
InputsPDF, images, DOCXPDF, images
Languages80+ languagesThai, English
Max pages per request1,000500
Tables✓ Yes✓ Yes
HandwritingNoNo
Math✓ YesNo
Bounding boxes✓ YesNo
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 feed mixed PDF and office documents into a RAG pipeline, especially inside LlamaIndex.
  • You want one hosted API with tiers, from 1 credit per page in Fast mode to 45 credits in Agentic Plus.
  • You want to start free: 10K credits per month, and re-parsing the same file within 48 hours costs nothing.

Choose Typhoon OCR if

  • Your documents are Thai or Thai-English, such as government forms, financial reports or books.
  • You want open weights you can self-host, with a 2B model or a 0.8B V2 variant, and no per-page fee.
  • You need tables as HTML with merged cells, equations as LaTeX and checkboxes marked.

Key differences

LlamaParseTyphoon OCR
LicenceProprietaryApache-2.0, subject to OpenTyphoon Terms and Conditions
How you run itHosted API onlySelf-host the weights, or use the Typhoon API (typhoon-ocr-v2)
Price$1.25 per 1,000 credits; about $1.25 to $56 per 1,000 pages depending on tier; 10K free credits per monthFree to self-host (you pay for compute); API pricing not published on the model card
Output formatsMarkdown, JSON, plain text, imagesMarkdown, HTML, LaTeX
BenchmarksNot publishedAuthor-reported: 84.7 olmOCR-bench, 90.97 OmniDocBench v1.6, 59.9 ThaiOCRBench (V2 2B)
Language scopeNot publishedThai and English only; no other languages evaluated
Known failureInvented transactions on bank statements (#450); hallucination on low-quality scans with no confidence score (#483); jobs stuck for days and premium mode taking 4 to 5 minutes (#623)V2 can loop until the token limit on dense multi-column pages; can output text not in the image; GGUF builds may lose accuracy

Sources

What each one is

LlamaParse

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

LlamaParse details

Typhoon OCR

Open vision model tuned for Thai and English documents, with Markdown output.

Typhoon OCR 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": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

LlamaParse alternativesTyphoon OCR alternativesBest OCR models in 2026