Alibaba

Qwen-VL OCR

Name: Qwen-VL OCR
Brand: Alibaba

Canonical ID: alibaba/qwen-vl-ocr

More Alibaba models More qwen-vl-ocr family models

OCR model for extracting structured text from documents and screenshots

Reasoning: No Tool use: No

Overview

text image

Provider: Alibaba
Family: qwen-vl-ocr
Release date: 2024-10-28
Last updated: 2025-04-13
Input modalities: text, image
Output modalities: text

Pricing and Limits

Token pricing

Input: $0.72/1M
Output: $0.72/1M
Cached input: N/A

Context and output

Context window: 34,096
Max output tokens: 4,096
Qualified ID: alibaba/qwen-vl-ocr

Model Summary

Qwen-VL OCR is a model listing in the Alibaba provider catalog. It is categorized under the qwen-vl-ocr family.

The model supports text, image modalities across input/output paths. Reported context capacity is 34,096. Pricing is listed at $0.72/1M input and $0.72/1M output.

Same Family: qwen-vl-ocr

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output	Flags
Qwen-VL OCR alibaba_cn/qwen-vl-ocr	Alibaba (China)	34,096	$0.717/1M	$0.717/1M

Qwen-VL OCR

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Alibaba

DeepSeek V4 Flash 0731

GLM-5.2

Kimi K3

QVQ Max

Qwen2.5 14B Instruct

Qwen2.5 32B Instruct

Qwen2.5 72B Instruct

Qwen2.5 7B Instruct

Same Family: qwen-vl-ocr