Models ▼
Products Features Pricing Download Compare API FAQ Login Get API Key →
Qwen 3.6 - Now Available

Introducing Qwen LLM
Next-Gen AI Intelligence

Qwen is a frontier multimodal AI model developed by Alibaba's Tongyi Lab. Engineered for real world complexity, it combines 512K token context, 130+ language support, native vision & video understanding, and state-of-the art coding & reasoning available as open weights or via a scalable, developer first API.

235K+
Context Window
110+
Languages
100M+
Monthly Users
Top 3
Global Rankings

Experience Qwen Live

See how Qwen understands, reasons, and generates - try a sample conversation.

Qwen Chat - Live Demo
Write a Python function to reverse a linked list
U
Q

Here's an efficient iterative solution:

def reverse_linked_list(head):
    prev = None
    current = head
    while current:
        next_node = current.next
        current.next = prev
        prev = current
        current = next_node
    return prev

Time complexity: O(n), Space: O(1). The algorithm reverses pointers in-place without using extra memory.

Qwen Ecosystem

Eight powerful products designed to accelerate your AI journey - from chat and code to video, voice, and mobile apps

💬

Qwen Chat

Conversational AI with comprehensive capabilities including chatbot interactions, image and video understanding, image generation, document processing, web search integration, tool utilization, and artifact creation.

  • Multi-turn conversation with memory
  • Image & Video analysis
  • Document & PDF processing
  • Web search integration
  • Tool calling & agent capabilities
  • Artifact generation & editing
💻

Qwen Code

AI-powered coding assistant that understands your codebase, generates high-quality code across 100+ programming languages, debugs issues, and helps refactor complex systems with intelligent suggestions.

  • Code completion & generation
  • Multi-language support (100+)
  • Code review & debugging
  • Repository-level understanding
  • IDE integrations (VS Code, JetBrains)
  • Test generation & documentation
🔬

Qwen Research

Advanced AI research toolkit for scientists and analysts. Deep research capabilities with web search, academic paper analysis, data visualization, and comprehensive report generation.

  • Deep web research agent
  • Academic paper analysis
  • Data extraction & visualization
  • Literature review automation
  • Multi-source fact verification
  • Research report generation
🔧

API Platform

Enterprise-grade API platform with scalable infrastructure, real-time streaming, batch processing, fine-tuning capabilities, and comprehensive monitoring for production AI applications.

  • RESTful & GraphQL APIs
  • Real-time streaming support
  • Model fine-tuning pipeline
  • Enterprise SLA (99.95% uptime)
  • Usage analytics & monitoring
  • Multi-region deployment
🎬

Qwen AI Video Generator

Turn text prompts and reference images into cinematic, high-fidelity videos. Generate short clips, animations, product demos, and social-ready content with precise motion control and style consistency.

  • Text-to-video & image-to-video
  • Up to 1080p HD output
  • Camera motion & style presets
  • Character & scene consistency
  • Lip-sync & voice-over integration
  • Commercial usage rights
🎙️

Qwen AI Voice

Natural-sounding text-to-speech, voice cloning, and real-time speech recognition. Build voice assistants, audiobooks, dubbing pipelines, and accessibility tools in 50+ languages with emotion control.

  • Voice cloning from 10s of audio
  • 50+ languages & 200+ voices
  • Emotion & style control
  • Real-time streaming TTS
  • Speech-to-text transcription
  • Custom voice fine-tuning
📲

Qwen AI App

Native mobile apps for iOS and Android. Chat, scan documents, ask visual questions, transcribe meetings, and access every Qwen capability on the go - with seamless cross-device sync.

  • iOS 15+ and Android 9+ support
  • Offline voice & vision modes
  • Camera-based visual Q&A
  • Real-time meeting transcription
  • Document & PDF scanning
  • Cross-device chat sync
📦

Qwen AI APK

Direct Android APK download for users in regions without Google Play access, or for sideloading on Android TV, tablets, and custom ROMs. Always-current, signed builds verified by our security team.

  • Latest stable & beta channels
  • ARM64, ARMv7 & x86_64 builds
  • Signed & checksum-verified
  • Auto-update support
  • Android 9+ (TV & tablet ready)
  • No Google Services required

Frontier Model Comparison

Technical specifications and performance benchmarks across leading large language models as of Q2 2026. Metrics are based on published technical reports, independent evaluations, and community benchmarks.

Model Architecture Context Window Languages MMLU (5-shot) Code (HumanEval) Math (GSM8K) Inference Speed Access Tier Release
ChatGPT 5.4 Dense + MoE Hybrid 256K tokens 95+ 94.2% 91.5% 96.8% ~85 tok/s Closed Mar 2026
Claude Opus 4.5 Sparse MoE 200K tokens 80+ 93.1% 92.8% 95.4% ~72 tok/s API Only Feb 2026
Kimi-K2.5 Hybrid Attention 1M tokens 100+ 91.7% 88.3% 93.2% ~65 tok/s API + Enterprise Jan 2026
Gemma 4 Dense Transformer 256K tokens 100+ 89.7% 91.8% 94.2% ~65 tok/s Open Weights Mar 2026
DeepSeek V4 Sparse MoE + MLA 256K tokens 100+ 93.6% 94.1% 97.4% ~128 tok/s Open Weights Mar 2026
GLM5 GLM Architecture v5 128K tokens 110+ 92.4% 90.1% 94.7% ~78 tok/s Open Weights Dec 2025
Qwen3.5-397B-A17B Dynamic MoE (397B/17B active) 256K tokens 120+ 93.8% 91.9% 97.1% ~95 tok/s Open Weights Nov 2025
Qwen3.6-Plus New Adaptive MoE + Structured Reasoning 512K tokens 130+ 94.9% 93.4% 97.8% ~112 tok/s Open Weights + API Apr 2026

Why Choose Qwen LLM?

Built with cutting-edge technology for the most demanding AI applications

⚡ Performance

Frontier-Class Reasoning

Qwen 3.6 delivers state-of-the-art results across reasoning, math, and code benchmarks - outperforming leading proprietary models while remaining open and accessible.

94.9% MMLU Score
97.8% Math (GSM8K)
93.4% HumanEval
🌐 Scale

Built for the Real World

Whether you're processing entire codebases, multi-document legal archives, or hour-long video transcripts, Qwen handles it natively with a massive 512K context window and 130+ language support.

512K Tokens Context
130+ Languages
~112 Tokens/sec
🧠

Advanced Reasoning

Multi-step logical reasoning with chain-of-thought processing for complex problem solving

🌍

Multilingual Mastery

Support for 130+ languages with native-level understanding and generation

👁️

Visual Intelligence

Image and video understanding with detailed analysis, OCR, and spatial reasoning

🎨

Image Generation

Create stunning, high-resolution images from text prompts with artistic control

📄

Document Processing

Extract, summarize, and analyze documents including PDFs, spreadsheets, and presentations

🔍

Web Search

Real-time web search integration with source citations and fact-checking

🛠️

Tool Utilization

Native function calling with support for custom tools, APIs, and external integrations

🏗️

Artifacts

Generate, preview, and edit code, documents, and interactive content in real-time

🔒

Enterprise Security

SOC 2 compliant, data encryption, role-based access, and private deployment options

Lightning Fast

Optimized inference with sub-100ms latency and high throughput for real-time applications

📊

Long Context

Process up to 512K tokens in a single context window for massive document analysis

🤝

Agentic Workflows

Autonomous multi-agent orchestration for complex, multi-step task execution

🎙️

Voice & Audio

Native speech recognition, voice cloning, and natural voice generation in 50+ languages

🎯

Fine-Tuning

Customize Qwen on your data with LoRA, QLoRA, and full fine-tuning workflows

📡

Streaming Output

Server-sent events and WebSocket streaming for real-time generation in production apps

Simple, Transparent Pricing

Start free and scale as you grow. No hidden fees, no credit card required to get started.

Monthly
Yearly Save 20%
Free
Starter

Perfect for trying out Qwen and personal projects

$ 0 /forever

No credit card required

  • 50 chat messages per day
  • Access to Qwen 3.4 model
  • Basic image understanding
  • Document upload (10 MB)
  • Community support
  • API access
  • Fine-tuning
Get Started Free
Team
Team

For teams collaborating on AI-powered workflows

$ 60 /user/mo

Minimum 3 seats

  • Everything in Pro, plus:
  • Shared workspaces & projects
  • Team admin dashboard
  • $50 monthly API credit per user
  • Custom system prompts
  • Audit logs & usage analytics
  • SSO & SAML authentication
Start Team Trial
Enterprise
Enterprise

Custom deployments for large organizations

Custom

Tailored to your needs

  • Everything in Team, plus:
  • Dedicated infrastructure
  • Private cloud or on-premise
  • Custom fine-tuning included
  • 99.95% uptime SLA
  • Dedicated solutions engineer
  • 24/7 enterprise support
Contact Sales

Pay-As-You-Go API Pricing

Per-token pricing for developers building production applications

Model
Input
Output
Context
Best For
Qwen-Turbo
$0.10 / 1M tokens
$0.30 / 1M tokens
128K
High-volume tasks
Qwen-Plus
$0.50 / 1M tokens
$1.50 / 1M tokens
256K
General purpose
Qwen-Max
$2.00 / 1M tokens
$6.00 / 1M tokens
512K
Complex reasoning
Qwen-VL (Vision)
$0.80 / 1M tokens
$2.40 / 1M tokens
128K
Image & video
Qwen-Coder
$0.40 / 1M tokens
$1.20 / 1M tokens
256K
Code generation

Get Qwen on Any Platform

Choose how you want to use Qwen - chat app, IDE plugin, CLI, or local model. Step-by-step guides for every setup.

🪟

Windows

Windows 10 / 11 (64-bit)
~180 MB

⬇ Download .exe
🍎

macOS

macOS 12+ (Intel & Apple Silicon)
~165 MB

⬇ Download .dmg
🐧

Linux

Ubuntu, Debian, Fedora, Arch
~155 MB

⬇ AppImage / .deb
📱

Mobile

iOS 15+ & Android 9+
~80 MB

⬇ App Store / Play

Install Qwen Desktop on Windows

Native Windows app with full GPU acceleration and offline support.

  1. Download the installer

    Grab the latest signed .exe from our official release page.

    # Direct download (PowerShell) PS> Invoke-WebRequest -Uri "https://qwen3lm.com/download/Qwen-Setup.exe" -OutFile "Qwen-Setup.exe"
  2. Run the installer

    Double-click Qwen-Setup.exe and follow the wizard. The installer auto-detects CUDA / DirectML for GPU acceleration.

  3. Sign in & start chatting

    Launch Qwen from the Start Menu, sign in with your free account, and pick a model. Conversations sync across devices.

Install Qwen Desktop on macOS

Universal binary - optimized for Apple Silicon (M-series) and Intel Macs.

  1. Download the DMG

    Use Homebrew for the fastest install, or grab the .dmg directly.

    # Option A - Homebrew (recommended) $ brew install --cask qwen # Option B - Direct download $ curl -LO https://qwen3lm.com/download/Qwen.dmg
  2. Drag to Applications

    Open the DMG and drag Qwen.app into your /Applications folder. On first launch, right-click → Open to bypass Gatekeeper.

  3. Grant permissions

    For voice and screen features, grant Microphone and Screen Recording access in System Settings → Privacy & Security.

Install Qwen Desktop on Linux

Available as AppImage (universal), .deb (Debian/Ubuntu), and .rpm (Fedora/RHEL).

  1. Download for your distro
    # Debian / Ubuntu $ wget https://qwen3lm.com/download/qwen_latest_amd64.deb $ sudo dpkg -i qwen_latest_amd64.deb # Fedora / RHEL $ sudo dnf install https://qwen3lm.com/download/qwen-latest.x86_64.rpm # Arch (AUR) $ yay -S qwen-desktop
  2. Or use AppImage (any distro)
    $ chmod +x Qwen-x86_64.AppImage $ ./Qwen-x86_64.AppImage
  3. Launch Qwen

    Run qwen from your terminal or launch via the Activities/Apps menu.

Install Qwen on iOS & Android

Native mobile apps with offline voice mode, camera vision, and cross-device sync.

  1. Download from your app store

    Search "Qwen Chat" in the App Store (iOS 15+) or Google Play (Android 9+). Or scan the QR code below.

    # Direct links iOS: https://apps.apple.com/app/qwen-chat Android: https://play.google.com/store/apps/details?id=ai.qwen.chat APK: https://qwen3lm.com/download/qwen-android.apk
  2. Sign in to sync

    Use the same account as your desktop or web app - all conversations, files, and custom prompts sync automatically.

  3. Enable mobile-specific features

    Allow camera, microphone, and notifications to use vision Q&A, voice chat, and live transcription.

Install the Python SDK

The official Python client for Qwen API. Works with Python 3.8+.

  1. Install via pip
    $ pip install qwen-sdk # Or with optional extras for vision & audio $ pip install "qwen-sdk[vision,audio]"
  2. Set your API key
    $ export QWEN_API_KEY="sk-your-key-here"
  3. Make your first call
    from qwen import Qwen client = Qwen() response = client.chat.completions.create( model="qwen-3.6", messages=[{"role": "user", "content": "Hello, Qwen!"}] ) print(response.choices[0].message.content)

Install the Node.js SDK

Official TypeScript/JavaScript client. Works with Node 18+, Bun, and Deno.

  1. Install via npm, pnpm, or yarn
    $ npm install @qwen/sdk # or $ pnpm add @qwen/sdk $ yarn add @qwen/sdk
  2. Configure your environment

    Add your API key to a .env file or set it as an environment variable.

    # .env QWEN_API_KEY="sk-your-key-here"
  3. Make your first request
    import { Qwen } from "@qwen/sdk"; const client = new Qwen(); const res = await client.chat.completions.create({ model: "qwen-3.6", messages: [{ role: "user", content: "Hello!" }] }); console.log(res.choices[0].message.content);

Run Qwen with Docker

Spin up a local Qwen inference server in seconds. Works with Docker Desktop and Podman.

  1. Pull the official image
    $ docker pull qwenlm/qwen-server:latest
  2. Run the container

    Mount a volume for model cache and expose port 8000. Add --gpus all for NVIDIA GPU support.

    $ docker run -d \ --name qwen \ --gpus all \ -p 8000:8000 \ -v qwen-models:/root/.cache/qwen \ qwenlm/qwen-server:latest \ --model qwen-3.6-7b
  3. Test the endpoint
    $ curl http://localhost:8000/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{"model":"qwen-3.6-7b","messages":[{"role":"user","content":"Hi"}]}'

Run Qwen Locally (Open Weights)

Run open-source Qwen models on your own hardware with Ollama, llama.cpp, or Hugging Face Transformers.

  1. Option A - Ollama (easiest)

    One-command install and run. Great for laptops and workstations.

    # Install Ollama, then: $ ollama pull qwen3:7b $ ollama run qwen3:7b
  2. Option B - Hugging Face Transformers
    $ pip install transformers accelerate torch from transformers import AutoModelForCausalLM, AutoTokenizer model_name = "Qwen/Qwen3-7B-Instruct" tokenizer = AutoTokenizer.from_pretrained(model_name) model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
  3. Option C - llama.cpp (GGUF quantized)

    Best for low-RAM devices. Download GGUF weights from Hugging Face and run with llama.cpp.

    $ ./llama-cli -m qwen3-7b-q4_k_m.gguf -p "Hello Qwen" -n 256

System Requirements

Minimum specs to run Qwen smoothly across deployment options

💻 Desktop & Mobile
  • OSWin 10+, macOS 12+, Linux
  • RAM4 GB minimum
  • Disk500 MB free
  • NetworkBroadband (cloud mode)
🔧 API & SDK
  • Python3.8 or higher
  • Node.js18 LTS or higher
  • API KeyFree at qwen3lm.com
  • AuthBearer token (HTTPS)
Local Inference
  • RAM (7B model)8 GB (16 GB rec.)
  • GPU VRAM6 GB+ (optional)
  • Disk~15 GB per model
  • CUDA / MetalSupported

Start Building Today

Integrate Qwen's powerful AI capabilities into your applications with just a few lines of code. Get started with free credits.

# Install the Qwen SDK
pip install qwen-sdk

# Make your first API call
from qwen import Qwen

client = Qwen(api_key="your-api-key")

response = client.chat.completions.create(
  model="qwen-3.6",
  messages=[{"role": "user", "content": "Hello, Qwen!"}]
)

print(response.choices[0].message.content)

Frequently Asked Questions

Everything you need to know about Qwen LLM

Qwen LLM is a family of large language models developed by Alibaba Group's Tongyi Lab. It includes models like Qwen 3.6, 3.5, and 3.4, offering capabilities in natural language understanding, code generation, visual analysis, and more. Qwen is available both as open-source models and through cloud APIs.

Yes! Qwen Chat offers a generous free tier with access to most features including chat, image understanding, document processing, and web search. The API platform also provides free credits for new users. Open-source weights are freely available under the Apache 2.0 license for certain model sizes.

Qwen offers some of the most competitive pricing in the industry. Qwen-Turbo starts at just $0.10 per million input tokens - significantly less than equivalent tiers from OpenAI or Anthropic. Combined with open-source availability, you get flagship performance at a fraction of the cost.

Qwen 3.6 matches or exceeds leading models in many benchmarks, particularly in multilingual understanding, coding tasks, and cost-efficiency. It offers a larger context window (512K tokens), supports 130+ languages, and provides open-source availability - features not matched by most competitors. See our comparison table above for detailed metrics.

Absolutely. Qwen's open-source models are available under the Apache 2.0 license, allowing commercial use. For API-based access, we offer flexible pricing plans including enterprise SLAs, dedicated infrastructure, and custom fine-tuning options for production workloads.

Qwen Chat supports a wide range of document formats including PDF, DOCX, XLSX, PPTX, TXT, CSV, Markdown, HTML, and more. It can extract text, summarize content, answer questions about documents, and even analyze tables and charts within files.

Getting started is simple: 1) Sign up at platform.qwenlm.ai, 2) Generate your API key, 3) Install our SDK (pip install qwen or npm install @qwen/sdk), and 4) Make your first API call. We provide comprehensive documentation, code examples in Python, JavaScript, and more, plus community support channels.

Yes, Qwen API supports Server-Sent Events (SSE) streaming for real-time token generation. This enables live chat experiences, progressive document analysis, and streaming code completion. WebSocket support is also available for bidirectional communication.

Qwen Code is a specialized coding assistant built on Qwen's foundation models, optimized for software development. It features repository-level understanding (not just single files), supports 100+ programming languages, integrates with VS Code and JetBrains IDEs, and achieves state-of-the-art scores on HumanEval and other coding benchmarks.

Sign In to Qwen AI

Access your conversations, API keys, and workspace from any device. One account unlocks chat, code, voice, video, and API tools.