OCRRouter

Qwen-VL vs Typhoon OCR

Pick Typhoon OCR for Thai and English documents such as government forms, financial reports and books. It is a 2B model that scores 84.7 on olmOCR-bench, against 64.6 for Qwen 3 VL 8B in the independent Datalab table. Pick Qwen-VL when you need OCR in many languages, or one model that also does reasoning and VQA on photos and screenshots, and add loop checks for scans.

Qwen-VLqwen/qwen-vlTyphoon OCRtyphoon/typhoon-ocr
TypeOpen sourceOpen source
Price2 credits / page2 credits / page
Per 1,000 pages$2.00$2.00
Typical speed2.0 s / page1.8 s / page
Best forFlexible extraction with promptsThai documents
InputsPDF, imagesPDF, images
Languages30+ languagesThai, English
Max pages per request200500
Tables✓ Yes✓ Yes
Handwriting✓ YesNo
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 Qwen-VL if

  • It reads text in 32 languages, while Typhoon OCR has only been evaluated on Thai and English.
  • It comes in sizes from 2B to 235B-A22B MoE, all under Apache-2.0, so you can match the model to your GPU.
  • It handles OCR plus reasoning or VQA, and works on photos and screenshots with text, including low light, blur and tilted text per Qwen.

Choose Typhoon OCR if

  • It is built for Thai and Thai-English documents, and V1.5 beat GPT-5 and Gemini 2.5 Pro on Thai government forms (BLEU 0.870).
  • Its V2 2B scores 84.7 on olmOCR-bench, a figure the authors report, from a model far smaller than the Qwen sizes that have been benchmarked.
  • It outputs tables as HTML with merged cells, equations as LaTeX, and marks checkboxes.

Key differences

Qwen-VLTyphoon OCR
LanguagesOCR in 32 languagesThai and English only evaluated
Model sizes2B, 4B, 8B, 32B dense; 30B-A3B and 235B-A22B MoE2B (V2 and V1.5); 0.8B V2 variant
LicenceApache-2.0Apache-2.0, subject to OpenTyphoon Terms and Conditions
Output formatsPlain text, HTML, bounding boxes, JSON, MarkdownMarkdown, HTML, LaTeX
olmOCR-bench64.6 (Qwen 3 VL 8B, independent, Datalab table)84.7 (V2 2B, reported by the authors)
Hosted API pricingAlibaba Cloud Model Studio, varies by model, not verifiedTyphoon API (typhoon-ocr-v2), Not published
Known failureLoops repeating the same text, worse with greedy decoding and on low-quality scans; GGUF builds often get stuck on scanned documentsV2 can loop until the token limit on dense multi-column pages; key-information extraction is weakest, 21.0 on ThaiOCRBench

Sources

What each one is

Qwen-VL

Alibaba's open-weight vision language models (Qwen2.5-VL, Qwen3-VL). Strong general OCR and grounding.

Qwen-VL 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": "qwen/qwen-vl","fallbacks": ["typhoon/typhoon-ocr"],"file_url": "https://example.com/document.pdf"}

Questions

More comparisons

Qwen-VL alternativesTyphoon OCR alternativesBest OCR models in 2026