Qwen

Qwen: Qwen-VL OCR

qwen/qwen-vl-ocr

Access Qwen-VL OCR from Qwen using Puter.js AI API.

Get Started
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms", {
    model: "qwen/qwen-vl-ocr"
}).then(response => {
    document.body.innerHTML = response.message.content;
});
<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "qwen/qwen-vl-ocr"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.puter.com/puterai/openai/v1/",
    api_key="YOUR_PUTER_AUTH_TOKEN",
)

response = client.chat.completions.create(
    model="qwen/qwen-vl-ocr",
    messages=[
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
)

print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
  -d '{
    "model": "qwen/qwen-vl-ocr",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Qwen-VL OCR is Alibaba's specialized vision-language model purpose-built for text extraction and document parsing, derived from the Qwen-VL series.

Unlike general-purpose VL models, it's optimized for OCR across scanned documents, tables, receipts, exam papers, forms, and handwritten content. It supports multilingual recognition including English, Chinese, French, German, Japanese, Korean, Russian, Italian, and Arabic.

Capabilities include skewed image recognition, text localization with bounding box coordinates, table-to-HTML parsing, document-to-LaTeX conversion, and formula transcription. Built-in task modes return structured output as plain text, JSON, HTML, or LaTeX depending on the workflow.

It's the right Qwen API choice for developers building document digitization, receipt parsing, or information extraction pipelines that need OCR-focused accuracy rather than general visual reasoning.

Context Window 34K

tokens

Max Output 4K

tokens

Input Cost $0.72

per million tokens

Output Cost $0.72

per million tokens

Input text, image

modalities

Tool Use No

 

Knowledge Cutoff Apr 2024

 

Release Date Oct 28, 2024

 

Model Playground

Try Qwen-VL OCR instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat qwen/qwen-vl-ocr
Qwen
Chat with Qwen-VL OCR
Powered by Puter.js

More AI Models From Qwen

Find other Qwen models

Chat

Qwen3.6 Flash

Qwen3.6 Flash is the speed-optimized tier of Alibaba's Qwen3.6 model family, designed for high-throughput, low-latency inference pipelines. It sits alongside Qwen3.6 Max Preview, Plus, and 35B-A3B in the product lineup, targeting use cases where fast response times matter more than peak benchmark scores. Like other Qwen3.6 models, it builds on a hybrid architecture combining linear attention with sparse mixture-of-experts routing. It is best suited for high-volume production workloads such as classification, extraction, summarization, and lightweight agent tasks where latency and cost efficiency are the primary constraints.

Chat

Qwen3.5 Plus 2026-04-20

Qwen3.5 Plus is a proprietary hosted model from Alibaba, built on the Qwen3.5-397B-A17B Mixture-of-Experts architecture with 397 billion total parameters and 17 billion active per token. Its headline feature is a 1-million-token native context window — among the largest available via API — making it well suited for processing entire codebases, long documents, or extended multi-turn conversations in a single request. It supports both a deep-thinking mode and an "Auto" mode that adaptively invokes tools like web search and code interpreters. This April 20, 2026 snapshot reflects ongoing improvements to the model since its original February 2026 launch. The Qwen3.5 series demonstrated strong multimodal performance across reasoning, coding, and vision tasks. A solid general-purpose option for developers needing large-context capabilities without migrating to the newer Qwen3.6 line.

Chat

Qwen3.6 27B

Qwen3.6 27B is a dense 27-billion-parameter multimodal model from Alibaba's Qwen team, purpose-built for agentic coding and repository-level reasoning. It scores 77.2% on SWE-bench Verified and 59.3% on Terminal-Bench 2.0, outperforming the previous-generation Qwen3.5-397B-A17B across all major coding benchmarks despite being far smaller. It natively supports text, image, and video inputs with a 262K-token context window, extendable to 1M tokens. A standout feature is Thinking Preservation, which retains reasoning traces across conversation turns — reducing redundant computation in multi-step agent loops. The model uses a hybrid attention architecture combining Gated DeltaNet with traditional self-attention. Ideal for developers building coding agents, multi-turn tool-use workflows, or frontend generation pipelines.

Frequently Asked Questions

How do I use Qwen-VL OCR?

You can access Qwen-VL OCR by Qwen through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.

Is Qwen-VL OCR free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Qwen-VL OCR to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Qwen-VL OCR?
Qwen-VL OCR costs $0.72 per 1M input tokens and $0.72 per 1M output tokens.
Price per 1M tokens
Input$0.72
Output$0.72
Who created Qwen-VL OCR?

Qwen-VL OCR was created by Qwen and released on Oct 28, 2024.

What is the context window of Qwen-VL OCR?

Qwen-VL OCR supports a context window of 34K tokens. For reference, that is roughly equivalent to 68 pages of text.

What is the max output length of Qwen-VL OCR?

Qwen-VL OCR can generate up to 4K tokens in a single response.

What is the knowledge cutoff of Qwen-VL OCR?

Qwen-VL OCR has a knowledge cutoff date of Apr 2024. This means the model was trained on data available up to that date.

What types of input can Qwen-VL OCR process?

Qwen-VL OCR accepts the following input types: text, image. It produces: text.

Does Qwen-VL OCR support tool use (function calling)?

No, Qwen-VL OCR does not currently support tool use (function calling).

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Qwen-VL OCR API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.

Get started with Puter.js

Add Qwen-VL OCR to your app without worrying about API keys or setup.

Read the Docs View Tutorials