Qwen VL Ocr
Qwen
qwen/qwen-vl-ocr
Professional OCR extraction
Context Window
32K
32,000 tokens
Max Output
8K
8,192 tokens
About this model
Qwen VL OCR is a vision-language model optimized for document OCR, excelling at accurate extraction of tables, forms, and document content.
Ideal for digitizing financial reports, scanned contracts, invoices, and other structured documents. Access via Chuizi.AI with a ck- API key.
Highlights
Professional OCR
Table extraction
Form recognition
Multi-language
Best For
Document digitizationInvoice processingContract extractionReport recognition
2025-09-01
Capabilities
ChatVision
Aliases
qwen-vl-ocrPricing (per 1M tokens)
| Pricing (per 1M tokens) | / 1M tokens |
|---|---|
| Input / 1M | $2.10 |
| Output / 1M | $5.25 |
Final prices shown
Quick Start
main.py
from openai import OpenAI client = OpenAI( base_url="https://api.chuizi.ai/v1", api_key="ck-your-key-here", ) response = client.chat.completions.create( model="qwen/qwen-vl-ocr", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)