Qwen3-VL 32B OCR

Alibaba Cloud, open modelqwen3-vl-32b-ocrModel source: Hugging Face

Document reading for awkward layouts: tables, columns and handwriting.

Reads in one go

≈ 140 pages

65,536 tokens

Brain size

Mid-sized

32B, NVFP4

Where it runs

Spain (EU)

MIG B200

Understands

Text and images

Vision, OCR

What it is good at

Vision. Reads images as well as text: photos, screenshots, scanned documents.
OCR. Pulls the text out of scanned documents, tables and columns included.

Pricing

€ per million tokens, VAT included

You send (input)0.10 €

It answers (output)0.35 €

1,000 chat answers~0.16 €

Analysing a 200 page contract~0.01 €

try it with 50 € freeActivated with your card. Enough for about 322,581 answers.

For your technical team

Compatible with the OpenAI SDK: change the base URL and the key, and that is it.

curl https://api.gpuflow.ai/v1/chat/completions \
  -H "Authorization: Bearer $GPUFLOW_API_KEY" \
  -d '{ "model": "qwen3-vl-32b-ocr",
        "messages": [{ "role": "user", "content": "Hola" }] }'