Qwen-VL OCR

Name: Qwen-VL OCR
Author: Alibaba

OCR model for extracting structured text from documents and screenshots

Live

Open / InstallLast updated August 5, 2026

Description

OCR model for extracting structured text from documents and screenshots. Supports a context window of 34,096 tokens. Input priced at $0.72 per million tokens. Weights are not publicly released; access is via the provider API.

Author

Alibaba

Platform

api

Pricing model

paid

Capabilities

Text generation
34,096 token context
Image input

Benchmarks

No benchmark results have been added yet.