Files
zeekay 1f308322ab Keep wide tables and specs inside a phone screen
At 390 pixels the blog's tables, the datasets tables and the model
card specs ran past the right edge, and body's overflow-x clip cut
them off rather than letting them scroll. Tables now scroll in their
own box, and a spec column shrinks and wraps instead of pushing its
neighbour out of the card.
2026-09-30 02:41:46 -07:00

114 lines
44 KiB
HTML
Raw Permalink Blame History

This file contains invisible Unicode characters
This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<!DOCTYPE html><!--_BoRG_r6Z3v9udL0lI0J_--><html lang="en"><head><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1"/><link rel="stylesheet" href="/_next/static/css/1d1f6bc532e5f43f.css" data-precedence="next"/><link rel="stylesheet" href="/_next/static/css/eb87e4f7aea490c6.css" data-precedence="next"/><link rel="preload" as="script" fetchPriority="low" href="/_next/static/chunks/webpack-f43ad49c79db3299.js"/><script src="/_next/static/chunks/4bd1b696-c023c6e3521b1417.js" async=""></script><script src="/_next/static/chunks/255-566af14aff71e752.js" async=""></script><script src="/_next/static/chunks/main-app-7eaab9f523b3767f.js" async=""></script><script src="/_next/static/chunks/619-ba102abea3e3d0e4.js" async=""></script><script src="/_next/static/chunks/app/layout-425ca81883167c16.js" async=""></script><script src="/_next/static/chunks/app/blog/%5Bslug%5D/page-38f8c2a205f98d97.js" async=""></script><script src="/assets/js/main.js" async=""></script><link rel="icon" type="image/svg+xml" href="/favicon.svg"/><link rel="alternate icon" href="/favicon.png"/><title>Qwen3-Coder: Agentic Coding in the World — Zen Blog</title><meta name="description" content="Today, we&#x27;re announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we&#x27;re excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports t"/><meta name="keywords" content="AI, LLM, Agentic AI, Code Generation, Zen Coder, Multimodal, Open Source, Machine Learning"/><meta name="data-upstream" content="true"/><script src="/_next/static/chunks/polyfills-42372ed130431b0a.js" noModule=""></script></head><body><div hidden=""><!--$--><!--/$--></div><header><nav class="navbar"><div class="container"><div class="logo"><a href="/"><svg class="enso logo-img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 100 100" width="34" height="34" fill="none" role="img" aria-label="Zen ensō"><defs><linearGradient id="_R_adb_" x1="12%" y1="0%" x2="88%" y2="100%"><stop offset="0%" stop-color="#ffffff"></stop><stop offset="50%" stop-color="#d4d4d8"></stop><stop offset="100%" stop-color="#7c7c82"></stop></linearGradient></defs><path class="enso-stroke" pathLength="1" d="M58 13 C38 9 17 22 13 44 C9 68 26 89 50 90 C74 91 91 74 89 50 C88 41 87 35 84 30" stroke="url(#_R_adb_)" stroke-width="7" stroke-linecap="round" stroke-linejoin="round"></path></svg><div class="logo-text"><h1>Zen LM</h1></div></a></div><div class="header-right"><div class="nav-links"><a class="" href="/">Home</a><div class="nav-item"><a class="" href="/models/">Models<svg class="nav-caret" width="11" height="11" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M6 9l6 6 6-6"></path></svg></a><div class="nav-dropdown"><div class="nav-dropdown-inner"><a class="dd-item" href="/models/#zen6"><div class="dd-item-text"><span class="dd-item-label">Zen 6<span class="dd-tag">Available</span></span><span class="dd-item-desc">27B dense — text, images and video, 1M context with YaRN</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="/models/#zen6"><div class="dd-item-text"><span class="dd-item-label">Zen 6 Flash<span class="dd-tag">Available</span></span><span class="dd-item-desc">The ternary Zen 6 — 5.95 GB, fits an Apple Silicon laptop</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="https://hanzo.ai/research-access" target="_blank" rel="noopener noreferrer"><div class="dd-item-text"><span class="dd-item-label">Zen 7<span class="dd-tag">Research preview</span></span><span class="dd-item-desc">No weights yet — request access</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="/models/#zen5"><div class="dd-item-text"><span class="dd-item-label">Earlier generations</span><span class="dd-item-desc">Zen 5, Zen 4 and Zen 3</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="/models/#catalog"><div class="dd-item-text"><span class="dd-item-label">All models</span><span class="dd-item-desc">Browse the full catalog</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a></div></div></div><div class="nav-item"><a class="" href="/datasets/">Datasets<svg class="nav-caret" width="11" height="11" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M6 9l6 6 6-6"></path></svg></a><div class="nav-dropdown"><div class="nav-dropdown-inner"><a class="dd-item" href="/datasets/"><div class="dd-item-text"><span class="dd-item-label">Zen Agentic Dataset<span class="dd-tag">New</span></span><span class="dd-item-desc">10B+ tokens of real tool use and reasoning</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="/datasets/"><div class="dd-item-text"><span class="dd-item-label">Training Data</span><span class="dd-item-desc">Curation, sources, and methodology</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="https://huggingface.co/datasets/hanzoai/zen-agentic-dataset" target="_blank" rel="noopener noreferrer"><div class="dd-item-text"><span class="dd-item-label">On HuggingFace</span><span class="dd-item-desc">Download and license the datasets</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a></div></div></div><div class="nav-item"><a class="" href="/research/">Research<svg class="nav-caret" width="11" height="11" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2.5" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M6 9l6 6 6-6"></path></svg></a><div class="nav-dropdown"><div class="nav-dropdown-inner"><a class="dd-item" href="/research/"><div class="dd-item-text"><span class="dd-item-label">Research Papers</span><span class="dd-item-desc">Technical reports across the Zen family</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="https://papers.zenlm.org" target="_blank" rel="noopener noreferrer"><div class="dd-item-text"><span class="dd-item-label">Papers Archive</span><span class="dd-item-desc">Full paper archive — papers.zenlm.org</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="/blog/"><div class="dd-item-text"><span class="dd-item-label">Blog</span><span class="dd-item-desc">Research notes, deep dives, and releases</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a></div></div></div><a class="active" href="/blog/">Blog</a></div><div class="logo-links"><a href="https://github.com/zenlm" target="_blank" rel="noopener noreferrer" class="icon-link" title="GitHub"><svg width="24" height="24" viewBox="0 0 24 24" fill="currentColor"><path d="M12 0c-6.626 0-12 5.373-12 12 0 5.302 3.438 9.8 8.207 11.387.599.111.793-.261.793-.577v-2.234c-3.338.726-4.033-1.416-4.033-1.416-.546-1.387-1.333-1.756-1.333-1.756-1.089-.745.083-.729.083-.729 1.205.084 1.839 1.237 1.839 1.237 1.07 1.834 2.807 1.304 3.492.997.107-.775.418-1.305.762-1.604-2.665-.305-5.467-1.334-5.467-5.931 0-1.311.469-2.381 1.236-3.221-.124-.303-.535-1.524.117-3.176 0 0 1.008-.322 3.301 1.23.957-.266 1.983-.399 3.003-.404 1.02.005 2.047.138 3.006.404 2.291-1.552 3.297-1.23 3.297-1.23.653 1.653.242 2.874.118 3.176.77.84 1.235 1.911 1.235 3.221 0 4.609-2.807 5.624-5.479 5.921.43.372.823 1.102.823 2.222v3.293c0 .319.192.694.801.576 4.765-1.589 8.199-6.086 8.199-11.386 0-6.627-5.373-12-12-12z"></path></svg></a><a href="https://huggingface.co/zenlm" target="_blank" rel="noopener noreferrer" class="icon-link" title="HuggingFace"><svg width="28" height="28" viewBox="0 0 32 32" fill="currentColor" aria-hidden="true"><circle cx="16" cy="16" r="13" fill="#d4d4d8"></circle><circle cx="11" cy="14" r="2" fill="#18181b"></circle><circle cx="21" cy="14" r="2" fill="#18181b"></circle><path d="M11 19 Q16 24 21 19" stroke="#18181b" stroke-width="1.6" fill="none" stroke-linecap="round"></path></svg></a></div><div class="nav-item try-item"><a href="https://hanzo.chat/?model=zen6" target="_blank" rel="noopener noreferrer" class="btn-try">Try Zen<svg width="16" height="16" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><div class="nav-dropdown nav-dropdown-right"><div class="nav-dropdown-inner"><a class="dd-item" href="https://hanzo.chat/?model=zen6" target="_blank" rel="noopener noreferrer"><div class="dd-item-text"><span class="dd-item-label">Zen 6<span class="dd-tag">Available</span></span><span class="dd-item-desc">Chat with Zen 6</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="https://hanzo.chat/?model=zen6-flash" target="_blank" rel="noopener noreferrer"><div class="dd-item-text"><span class="dd-item-label">Zen 6 Flash<span class="dd-tag">Available</span></span><span class="dd-item-desc">Chat with the ternary Zen 6</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="https://api.hanzo.ai" target="_blank" rel="noopener noreferrer"><div class="dd-item-text"><span class="dd-item-label">Zen API</span><span class="dd-item-desc">OpenAI- &amp; Anthropic-compatible. One key.</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a><a class="dd-item" href="https://hanzo.chat" target="_blank" rel="noopener noreferrer"><div class="dd-item-text"><span class="dd-item-label">Zen Chat</span><span class="dd-item-desc">Open the full chat experience</span></div><svg class="dd-arrow" width="14" height="14" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><path d="M5 12h14M13 6l6 6-6 6"></path></svg></a></div></div></div></div></div></nav></header><main><article class="blog-article" data-upstream=""><a class="blog-back" href="/blog/">← Blog</a><div class="blog-post-meta">July 21, 2025<!-- --> <!-- -->·<!-- --> <!-- -->5<!-- --> min read</div><h1 class="blog-post-title">Qwen3-Coder: Agentic Coding in the World</h1><p class="blog-post-lede">Today, we&#x27;re announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we&#x27;re excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports t</p><div class="blog-prose"><p><a href="https://github.com/QwenLM/Qwen3-Coder">GITHUB</a>
<a href="https://huggingface.co/Qwen">HUGGING FACE</a>
<a href="https://modelscope.cn/organization/qwen">MODELSCOPE</a>
<a href="https://discord.gg/yPEP2vHTu4">DISCORD</a></p>
<p>Today, we're announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we're excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports the context length of 256K tokens natively and 1M tokens with extrapolation methods, offering exceptional performance in both coding and agentic tasks. Qwen3-Coder-480B-A35B-Instruct sets new state-of-the-art results among open models on Agentic Coding, Agentic Browser-Use, and Agentic Tool-Use, comparable to Claude Sonnet 4.</p>
<div>
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Coder/qwen3-coder-main.jpg" alt="" width="800">
</div>
<p>Alongside the model, we're also open-sourcing a command-line tool for agentic coding: Qwen Code. Forked from Gemini Code, Qwen Code has been adapted with customized prompts and function calling protocols to fully unleash the capabilities of Qwen3-Coder on agentic coding tasks. Qwen3-Coder works seamlessly with the community’s best developer tools. As a foundation model, we hope it can be used anywhere across the digital world — Agentic Coding in the World!</p>
<h2 id="qwen3-coder">Qwen3-Coder</h2>
<h3 id="pre-training">Pre-Training</h3>
<p>There’s still room to scale in pretraining—and with Qwen3-Coder, we’re advancing along multiple dimensions to strengthen the model’s core capabilities:</p>
<ul>
<li>Scaling Tokens: 7.5T tokens (70% code ratio), excelling in coding while preserving general and math abilities.</li>
<li>Scaling Context: Natively supports 256K context and can be extended up to 1M with YaRN, optimized for repo-scale and dynamic data (e.g., Pull Requests) to empower Agentic Coding.</li>
<li>Scaling Synthetic Data: Leveraged Qwen2.5-Coder to clean and rewrite noisy data, significantly improving overall data quality.</li>
</ul>
<h3 id="post-training">Post-Training</h3>
<h4 id="scaling-code-rl-hard-to-solve-easy-to-verify">Scaling Code RL: Hard to Solve, Easy to Verify</h4>
<div>
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Coder/coderl.png" alt="" width="800">
</div>
Unlike the prevailing focus on competitive-level code generation in the community, we believe all code tasks are naturally well-suited for execution-driven large-scale reinforcement learning. That’s why we scaled up Code RL training on a broader set of real-world coding tasks. By automatically scaling test cases of diversity coding tasks, we created high-quality training instances and successfully unlocked the full potential of reinforcement learning. It not only significantly boosted code execution success rates, but also brought gains to other tasks. This encourages us to keep exploring hard-to-solve, easy-to-verify tasks as fertile ground for large-scale reinforcement learning.
<h4 id="scaling-long-horizon-rl">Scaling Long-Horizon RL</h4>
<div>
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Coder/swe.jpg" alt="" width="800">
</div>
<p>In real-world software engineering tasks like SWE-Bench, Qwen3-Coder must engage in multi-turn interaction with the environment, involving planning, using tools, receiving feedback, and making decisions. In the post-training phase of Qwen3-Coder, we introduced long-horizon RL (Agent RL) to encourage the model to solve real-world tasks through multi-turn interactions using tools. The key challenge of Agent RL lies in environment scaling. To address this, we built a scalable system capable of running 20,000 independent environments in parallel, leveraging Alibaba Cloud's infrastructure. The infrastructure provides the necessary feedback for large-scale reinforcement learning and supports evaluation at scale. As a result, Qwen3-Coder achieves state-of-the-art performance among open-source models on SWE-Bench Verified without test-time scaling.</p>
<h2 id="code-with-qwen3-coder">Code with Qwen3-Coder</h2>
<h3 id="qwen-code">Qwen Code</h3>
<p>Qwen Code is a research-purpose CLI tool adapted from Gemini CLI, with enhanced parser and tool support for Qwen-Coder models.</p>
<p>Make sure you have installed nodejs 20+:</p>
<p>You could install it via the following commands:</p>
<pre><code class="language-bash">curl -qL https://www.npmjs.com/install.sh | sh
</code></pre>
<p>Then install Qwen code via npm manager:</p>
<pre><code class="language-bash">npm i -g @qwen-code/qwen-code
</code></pre>
<blockquote>
<p>The other way is to install from the source:</p>
<pre><code class="language-bash">git clone https://github.com/QwenLM/qwen-code.git
cd qwen-code &#x26;&#x26; npm install &#x26;&#x26; npm install -g
</code></pre>
</blockquote>
<p>Qwen Code supports the OpenAI SDK when calling LLMs, and you can export the following environment variables or simply put them under the <code>.envfile</code>.</p>
<pre><code class="language-bash">export OPENAI_API_KEY="your_api_key_here"
export OPENAI_BASE_URL="https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
export OPENAI_MODEL="qwen3-coder-plus"
</code></pre>
<p>Now enjoy your vibe coding with Qwen-Code and Qwen, by simply typing: qwen!</p>
<h3 id="claude-code">Claude Code</h3>
<p>In addition to Qwen Code, you can now use Qwen3‑Coder with Claude Code. Simply request an API key on <a href="https://modelstudio.console.alibabacloud.com/">Alibaba Cloud Model Studio</a> platform and install Claude Code to start coding.</p>
<pre><code class="language-bash">npm install -g @anthropic-ai/claude-code
</code></pre>
<p>We have provided two entrypoints for seamlessly experiencing coding with Qwen3-Coder.</p>
<h4 id="optional-1-claude-code-proxy-api">Optional 1: Claude Code proxy API</h4>
<pre><code class="language-bash">export ANTHROPIC_BASE_URL=https://dashscope-intl.aliyuncs.com/api/v2/apps/claude-code-proxy
export ANTHROPIC_AUTH_TOKEN=your-dashscope-apikey
</code></pre>
<p>Then you should be able to use Claude Code with Qwen3-Coder!</p>
<h4 id="optional-2-claude-code-config-npm-package-for-router-customization">Optional 2: claude-code-config npm package for router customization</h4>
<p>claude-code-router aims for customizing different backend models for Claude Code. The dashscope team also provide a convenient config npm extension, namely claude-code-config, that provides default configuration for claude-code-router with DashScope support.
Run installation:</p>
<pre><code class="language-bash">npm install -g @musistudio/claude-code-router
npm install -g @dashscope-js/claude-code-config
</code></pre>
<p>and then run configuration:</p>
<pre><code class="language-bash">ccr-dashscope
</code></pre>
<p>The command will automatically generate the config json files and plugin directories for ccr. (You could also manually adjust these under ~/.claude-code-router/config.json and ~/.claude-code-router/plugins/ )
Start using claude code via ccr:</p>
<pre><code class="language-bash">ccr code
</code></pre>
<h3 id="cline">Cline</h3>
<p>Configure the Qwen3-Coder-480B-A35B-Instruct to cline
‒ Go to the Cline configuration settings
‒ For API Provider, select 'OpenAI Compatible'
‒ For the OpenAI Compatible API Key, enter the key obtained from Dashscope
‒ Check 'Use custom base URL' and enter: <code>https://dashscope-intl.aliyuncs.com/compatible-mode/v1</code>
‒ Enter <code>qwen3-coder-plus</code></p>
<video width="100%" muted controls="1">
<source src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Coder/qwen3_coder_plus_with_cline.mp4" type="video/mp4">
</video>
<h2 id="use-cases">Use Cases</h2>
<h2 id="api">API</h2>
<p>You can directly access the API of Qwen3-Coder through <a href="https://modelstudio.console.alibabacloud.com/">Alibaba Cloud Model Studio</a>. Here is a demonstration of how to use this model with the Qwen API.</p>
<pre><code class="language-python">import os
from openai import OpenAI
# Create client - using intl URL for users outside of China
# If you are in mainland China, use the following URL:
# "https://dashscope.aliyuncs.com/compatible-mode/v1"
client = OpenAI(
api_key=os.getenv("DASHSCOPE_API_KEY"),
base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)
prompt = "Help me create a web page for an online bookstore."
# Send request to qwen3-coder-plus model
completion = client.chat.completions.create(
model="qwen3-coder-plus",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": prompt}
],
)
# Print the response
print(completion.choices[0].message.content.strip())
</code></pre>
<h2 id="further-work">Further Work</h2>
<p>We are still actively working to improve the performance of our Coding Agent, aiming for it to take on more complex and tedious tasks in software engineering, thereby freeing up human productivity. More model sizes of Qwen3-Coder are on the way, delivering strong performance while reducing deployment costs. Additionally, we are actively exploring whether the Coding Agent can achieve self-improvement—an exciting and inspiring direction.</p></div></article></main><!--$--><!--/$--><footer><div class="container"><div class="footer-content"><div class="footer-section"><h4>Zen LM</h4><p>Open models from Zoo Labs Foundation, a 501(c)(3) non-profit, for agentic coding on your own machine and marketing work. Served on api.hanzo.ai.</p></div><div class="footer-section"><h4>Zen 6</h4><ul><li><a href="/models/#zen6">Zen 6</a></li><li><a href="/models/#zen6">Zen 6 Flash</a></li><li><a href="https://hanzo.ai/research-access" target="_blank" rel="noopener noreferrer">Zen 7 research preview</a></li></ul></div><div class="footer-section"><h4>Earlier Generations</h4><ul><li><a href="/models/#zen5">Zen 5</a></li><li><a href="/models/#zen4">Zen 4</a></li><li><a href="/models/#zen3">Zen 3</a></li></ul></div><div class="footer-section"><h4>Resources</h4><ul><li><a href="/datasets/">Training Data</a></li><li><a href="https://huggingface.co/zenlm" target="_blank" rel="noopener noreferrer">HuggingFace</a></li><li><a href="https://github.com/zenlm" target="_blank" rel="noopener noreferrer">GitHub</a></li><li><a href="/research/">Research Papers</a></li><li><a href="https://api.hanzo.ai" target="_blank" rel="noopener noreferrer">Zen API</a></li></ul></div></div><div class="footer-bottom"><p>© <!-- -->2026<!-- --> Zoo Labs Foundation, a 501(c)(3) non-profit. Zen LM open models.</p></div></div></footer><script src="/_next/static/chunks/webpack-f43ad49c79db3299.js" id="_R_" async=""></script><script>(self.__next_f=self.__next_f||[]).push([0])</script><script>self.__next_f.push([1,"1:\"$Sreact.fragment\"\n2:I[6529,[\"619\",\"static/chunks/619-ba102abea3e3d0e4.js\",\"177\",\"static/chunks/app/layout-425ca81883167c16.js\"],\"default\"]\n3:I[9766,[],\"\"]\n4:I[8924,[],\"\"]\n5:I[2619,[\"619\",\"static/chunks/619-ba102abea3e3d0e4.js\",\"953\",\"static/chunks/app/blog/%5Bslug%5D/page-38f8c2a205f98d97.js\"],\"\"]\n6:I[7405,[\"619\",\"static/chunks/619-ba102abea3e3d0e4.js\",\"177\",\"static/chunks/app/layout-425ca81883167c16.js\"],\"default\"]\na:I[7150,[],\"\"]\n:HL[\"/_next/static/css/1d1f6bc532e5f43f.css\",\"style\"]\n:HL[\"/_next/static/css/eb87e4f7aea490c6.css\",\"style\"]\n"])</script><script>self.__next_f.push([1,"0:{\"P\":null,\"b\":\"-BoRG_r6Z3v9udL0lI0J_\",\"p\":\"\",\"c\":[\"\",\"blog\",\"qwen3-coder\",\"\"],\"i\":false,\"f\":[[[\"\",{\"children\":[\"blog\",{\"children\":[[\"slug\",\"qwen3-coder\",\"d\"],{\"children\":[\"__PAGE__\",{}]}]}]},\"$undefined\",\"$undefined\",true],[\"\",[\"$\",\"$1\",\"c\",{\"children\":[[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/1d1f6bc532e5f43f.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]],[\"$\",\"html\",null,{\"lang\":\"en\",\"children\":[[\"$\",\"head\",null,{\"children\":[[\"$\",\"link\",null,{\"rel\":\"icon\",\"type\":\"image/svg+xml\",\"href\":\"/favicon.svg\"}],[\"$\",\"link\",null,{\"rel\":\"alternate icon\",\"href\":\"/favicon.png\"}]]}],[\"$\",\"body\",null,{\"children\":[[\"$\",\"$L2\",null,{}],[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":[[[\"$\",\"title\",null,{\"children\":\"404: This page could not be found.\"}],[\"$\",\"div\",null,{\"style\":{\"fontFamily\":\"system-ui,\\\"Segoe UI\\\",Roboto,Helvetica,Arial,sans-serif,\\\"Apple Color Emoji\\\",\\\"Segoe UI Emoji\\\"\",\"height\":\"100vh\",\"textAlign\":\"center\",\"display\":\"flex\",\"flexDirection\":\"column\",\"alignItems\":\"center\",\"justifyContent\":\"center\"},\"children\":[\"$\",\"div\",null,{\"children\":[[\"$\",\"style\",null,{\"dangerouslySetInnerHTML\":{\"__html\":\"body{color:#000;background:#fff;margin:0}.next-error-h1{border-right:1px solid rgba(0,0,0,.3)}@media (prefers-color-scheme:dark){body{color:#fff;background:#000}.next-error-h1{border-right:1px solid rgba(255,255,255,.3)}}\"}}],[\"$\",\"h1\",null,{\"className\":\"next-error-h1\",\"style\":{\"display\":\"inline-block\",\"margin\":\"0 20px 0 0\",\"padding\":\"0 23px 0 0\",\"fontSize\":24,\"fontWeight\":500,\"verticalAlign\":\"top\",\"lineHeight\":\"49px\"},\"children\":404}],[\"$\",\"div\",null,{\"style\":{\"display\":\"inline-block\"},\"children\":[\"$\",\"h2\",null,{\"style\":{\"fontSize\":14,\"fontWeight\":400,\"lineHeight\":\"49px\",\"margin\":0},\"children\":\"This page could not be found.\"}]}]]}]}]],[]],\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}],[\"$\",\"footer\",null,{\"children\":[\"$\",\"div\",null,{\"className\":\"container\",\"children\":[[\"$\",\"div\",null,{\"className\":\"footer-content\",\"children\":[[\"$\",\"div\",null,{\"className\":\"footer-section\",\"children\":[[\"$\",\"h4\",null,{\"children\":\"Zen LM\"}],[\"$\",\"p\",null,{\"children\":\"Open models from Zoo Labs Foundation, a 501(c)(3) non-profit, for agentic coding on your own machine and marketing work. Served on api.hanzo.ai.\"}]]}],[\"$\",\"div\",null,{\"className\":\"footer-section\",\"children\":[[\"$\",\"h4\",null,{\"children\":\"Zen 6\"}],[\"$\",\"ul\",null,{\"children\":[[\"$\",\"li\",null,{\"children\":[\"$\",\"$L5\",null,{\"href\":\"/models#zen6\",\"children\":\"Zen 6\"}]}],[\"$\",\"li\",null,{\"children\":[\"$\",\"$L5\",null,{\"href\":\"/models#zen6\",\"children\":\"Zen 6 Flash\"}]}],[\"$\",\"li\",null,{\"children\":[\"$\",\"a\",null,{\"href\":\"https://hanzo.ai/research-access\",\"target\":\"_blank\",\"rel\":\"noopener noreferrer\",\"children\":\"Zen 7 research preview\"}]}]]}]]}],[\"$\",\"div\",null,{\"className\":\"footer-section\",\"children\":[[\"$\",\"h4\",null,{\"children\":\"Earlier Generations\"}],[\"$\",\"ul\",null,{\"children\":[[\"$\",\"li\",null,{\"children\":[\"$\",\"$L5\",null,{\"href\":\"/models#zen5\",\"children\":\"Zen 5\"}]}],[\"$\",\"li\",null,{\"children\":[\"$\",\"$L5\",null,{\"href\":\"/models#zen4\",\"children\":\"Zen 4\"}]}],[\"$\",\"li\",null,{\"children\":[\"$\",\"$L5\",null,{\"href\":\"/models#zen3\",\"children\":\"Zen 3\"}]}]]}]]}],[\"$\",\"div\",null,{\"className\":\"footer-section\",\"children\":[[\"$\",\"h4\",null,{\"children\":\"Resources\"}],[\"$\",\"ul\",null,{\"children\":[[\"$\",\"li\",null,{\"children\":[\"$\",\"$L5\",null,{\"href\":\"/datasets\",\"children\":\"Training Data\"}]}],[\"$\",\"li\",null,{\"children\":[\"$\",\"a\",null,{\"href\":\"https://huggingface.co/zenlm\",\"target\":\"_blank\",\"rel\":\"noopener noreferrer\",\"children\":\"HuggingFace\"}]}],[\"$\",\"li\",null,{\"children\":[\"$\",\"a\",null,{\"href\":\"https://github.com/zenlm\",\"target\":\"_blank\",\"rel\":\"noopener noreferrer\",\"children\":\"GitHub\"}]}],[\"$\",\"li\",null,{\"children\":[\"$\",\"$L5\",null,{\"href\":\"/research\",\"children\":\"Research Papers\"}]}],[\"$\",\"li\",null,{\"children\":[\"$\",\"a\",null,{\"href\":\"https://api.hanzo.ai\",\"target\":\"_blank\",\"rel\":\"noopener noreferrer\",\"children\":\"Zen API\"}]}]]}]]}]]}],[\"$\",\"div\",null,{\"className\":\"footer-bottom\",\"children\":[\"$\",\"p\",null,{\"children\":[\"© \",2026,\" Zoo Labs Foundation, a 501(c)(3) non-profit. Zen LM open models.\"]}]}]]}]}],[\"$\",\"$L6\",null,{}],[\"$\",\"script\",null,{\"src\":\"/assets/js/main.js\",\"async\":true}]]}]]}]]}],{\"children\":[\"blog\",[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[[\"slug\",\"qwen3-coder\",\"d\"],[\"$\",\"$1\",\"c\",{\"children\":[null,[\"$\",\"$L3\",null,{\"parallelRouterKey\":\"children\",\"error\":\"$undefined\",\"errorStyles\":\"$undefined\",\"errorScripts\":\"$undefined\",\"template\":[\"$\",\"$L4\",null,{}],\"templateStyles\":\"$undefined\",\"templateScripts\":\"$undefined\",\"notFound\":\"$undefined\",\"forbidden\":\"$undefined\",\"unauthorized\":\"$undefined\"}]]}],{\"children\":[\"__PAGE__\",[\"$\",\"$1\",\"c\",{\"children\":[\"$L7\",[[\"$\",\"link\",\"0\",{\"rel\":\"stylesheet\",\"href\":\"/_next/static/css/eb87e4f7aea490c6.css\",\"precedence\":\"next\",\"crossOrigin\":\"$undefined\",\"nonce\":\"$undefined\"}]],\"$L8\"]}],{},null,false]},null,false]},null,false]},null,false],\"$L9\",false]],\"m\":\"$undefined\",\"G\":[\"$a\",[]],\"s\":false,\"S\":true}\n"])</script><script>self.__next_f.push([1,"b:I[4431,[],\"OutletBoundary\"]\nd:I[5278,[],\"AsyncMetadataOutlet\"]\nf:I[4431,[],\"ViewportBoundary\"]\n11:I[4431,[],\"MetadataBoundary\"]\n12:\"$Sreact.suspense\"\n8:[\"$\",\"$Lb\",null,{\"children\":[\"$Lc\",[\"$\",\"$Ld\",null,{\"promise\":\"$@e\"}]]}]\n9:[\"$\",\"$1\",\"h\",{\"children\":[null,[[\"$\",\"$Lf\",null,{\"children\":\"$L10\"}],null],[\"$\",\"$L11\",null,{\"children\":[\"$\",\"div\",null,{\"hidden\":true,\"children\":[\"$\",\"$12\",null,{\"fallback\":null,\"children\":\"$L13\"}]}]}]]}]\n"])</script><script>self.__next_f.push([1,"14:T2472,"])</script><script>self.__next_f.push([1,"\u003cp\u003e\u003ca href=\"https://github.com/QwenLM/Qwen3-Coder\"\u003eGITHUB\u003c/a\u003e\n\u003ca href=\"https://huggingface.co/Qwen\"\u003eHUGGING FACE\u003c/a\u003e\n\u003ca href=\"https://modelscope.cn/organization/qwen\"\u003eMODELSCOPE\u003c/a\u003e\n\u003ca href=\"https://discord.gg/yPEP2vHTu4\"\u003eDISCORD\u003c/a\u003e\u003c/p\u003e\n\u003cp\u003eToday, we're announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we're excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports the context length of 256K tokens natively and 1M tokens with extrapolation methods, offering exceptional performance in both coding and agentic tasks. Qwen3-Coder-480B-A35B-Instruct sets new state-of-the-art results among open models on Agentic Coding, Agentic Browser-Use, and Agentic Tool-Use, comparable to Claude Sonnet 4.\u003c/p\u003e\n\u003cdiv\u003e\n \u003cimg src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Coder/qwen3-coder-main.jpg\" alt=\"\" width=\"800\"\u003e\n\u003c/div\u003e\n\u003cp\u003eAlongside the model, we're also open-sourcing a command-line tool for agentic coding: Qwen Code. Forked from Gemini Code, Qwen Code has been adapted with customized prompts and function calling protocols to fully unleash the capabilities of Qwen3-Coder on agentic coding tasks. Qwen3-Coder works seamlessly with the community’s best developer tools. As a foundation model, we hope it can be used anywhere across the digital world — Agentic Coding in the World!\u003c/p\u003e\n\u003ch2 id=\"qwen3-coder\"\u003eQwen3-Coder\u003c/h2\u003e\n\u003ch3 id=\"pre-training\"\u003ePre-Training\u003c/h3\u003e\n\u003cp\u003eThere’s still room to scale in pretraining—and with Qwen3-Coder, we’re advancing along multiple dimensions to strengthen the model’s core capabilities:\u003c/p\u003e\n\u003cul\u003e\n\u003cli\u003eScaling Tokens: 7.5T tokens (70% code ratio), excelling in coding while preserving general and math abilities.\u003c/li\u003e\n\u003cli\u003eScaling Context: Natively supports 256K context and can be extended up to 1M with YaRN, optimized for repo-scale and dynamic data (e.g., Pull Requests) to empower Agentic Coding.\u003c/li\u003e\n\u003cli\u003eScaling Synthetic Data: Leveraged Qwen2.5-Coder to clean and rewrite noisy data, significantly improving overall data quality.\u003c/li\u003e\n\u003c/ul\u003e\n\u003ch3 id=\"post-training\"\u003ePost-Training\u003c/h3\u003e\n\u003ch4 id=\"scaling-code-rl-hard-to-solve-easy-to-verify\"\u003eScaling Code RL: Hard to Solve, Easy to Verify\u003c/h4\u003e\n\u003cdiv\u003e\n \u003cimg src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Coder/coderl.png\" alt=\"\" width=\"800\"\u003e\n\u003c/div\u003e\nUnlike the prevailing focus on competitive-level code generation in the community, we believe all code tasks are naturally well-suited for execution-driven large-scale reinforcement learning. That’s why we scaled up Code RL training on a broader set of real-world coding tasks. By automatically scaling test cases of diversity coding tasks, we created high-quality training instances and successfully unlocked the full potential of reinforcement learning. It not only significantly boosted code execution success rates, but also brought gains to other tasks. This encourages us to keep exploring hard-to-solve, easy-to-verify tasks as fertile ground for large-scale reinforcement learning.\n\u003ch4 id=\"scaling-long-horizon-rl\"\u003eScaling Long-Horizon RL\u003c/h4\u003e\n\u003cdiv\u003e\n \u003cimg src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Coder/swe.jpg\" alt=\"\" width=\"800\"\u003e\n\u003c/div\u003e\n\u003cp\u003eIn real-world software engineering tasks like SWE-Bench, Qwen3-Coder must engage in multi-turn interaction with the environment, involving planning, using tools, receiving feedback, and making decisions. In the post-training phase of Qwen3-Coder, we introduced long-horizon RL (Agent RL) to encourage the model to solve real-world tasks through multi-turn interactions using tools. The key challenge of Agent RL lies in environment scaling. To address this, we built a scalable system capable of running 20,000 independent environments in parallel, leveraging Alibaba Cloud's infrastructure. The infrastructure provides the necessary feedback for large-scale reinforcement learning and supports evaluation at scale. As a result, Qwen3-Coder achieves state-of-the-art performance among open-source models on SWE-Bench Verified without test-time scaling.\u003c/p\u003e\n\u003ch2 id=\"code-with-qwen3-coder\"\u003eCode with Qwen3-Coder\u003c/h2\u003e\n\u003ch3 id=\"qwen-code\"\u003eQwen Code\u003c/h3\u003e\n\u003cp\u003eQwen Code is a research-purpose CLI tool adapted from Gemini CLI, with enhanced parser and tool support for Qwen-Coder models.\u003c/p\u003e\n\u003cp\u003eMake sure you have installed nodejs 20+:\u003c/p\u003e\n\u003cp\u003eYou could install it via the following commands:\u003c/p\u003e\n\u003cpre\u003e\u003ccode class=\"language-bash\"\u003ecurl -qL https://www.npmjs.com/install.sh | sh\n\u003c/code\u003e\u003c/pre\u003e\n\u003cp\u003eThen install Qwen code via npm manager:\u003c/p\u003e\n\u003cpre\u003e\u003ccode class=\"language-bash\"\u003enpm i -g @qwen-code/qwen-code\n\u003c/code\u003e\u003c/pre\u003e\n\u003cblockquote\u003e\n\u003cp\u003eThe other way is to install from the source:\u003c/p\u003e\n\u003cpre\u003e\u003ccode class=\"language-bash\"\u003egit clone https://github.com/QwenLM/qwen-code.git\ncd qwen-code \u0026#x26;\u0026#x26; npm install \u0026#x26;\u0026#x26; npm install -g\n\u003c/code\u003e\u003c/pre\u003e\n\u003c/blockquote\u003e\n\u003cp\u003eQwen Code supports the OpenAI SDK when calling LLMs, and you can export the following environment variables or simply put them under the \u003ccode\u003e.envfile\u003c/code\u003e.\u003c/p\u003e\n\u003cpre\u003e\u003ccode class=\"language-bash\"\u003eexport OPENAI_API_KEY=\"your_api_key_here\"\nexport OPENAI_BASE_URL=\"https://dashscope-intl.aliyuncs.com/compatible-mode/v1\"\nexport OPENAI_MODEL=\"qwen3-coder-plus\"\n\u003c/code\u003e\u003c/pre\u003e\n\u003cp\u003eNow enjoy your vibe coding with Qwen-Code and Qwen, by simply typing: qwen!\u003c/p\u003e\n\u003ch3 id=\"claude-code\"\u003eClaude Code\u003c/h3\u003e\n\u003cp\u003eIn addition to Qwen Code, you can now use Qwen3‑Coder with Claude Code. Simply request an API key on \u003ca href=\"https://modelstudio.console.alibabacloud.com/\"\u003eAlibaba Cloud Model Studio\u003c/a\u003e platform and install Claude Code to start coding.\u003c/p\u003e\n\u003cpre\u003e\u003ccode class=\"language-bash\"\u003enpm install -g @anthropic-ai/claude-code\n\u003c/code\u003e\u003c/pre\u003e\n\u003cp\u003eWe have provided two entrypoints for seamlessly experiencing coding with Qwen3-Coder.\u003c/p\u003e\n\u003ch4 id=\"optional-1-claude-code-proxy-api\"\u003eOptional 1: Claude Code proxy API\u003c/h4\u003e\n\u003cpre\u003e\u003ccode class=\"language-bash\"\u003eexport ANTHROPIC_BASE_URL=https://dashscope-intl.aliyuncs.com/api/v2/apps/claude-code-proxy\nexport ANTHROPIC_AUTH_TOKEN=your-dashscope-apikey\n\u003c/code\u003e\u003c/pre\u003e\n\u003cp\u003eThen you should be able to use Claude Code with Qwen3-Coder!\u003c/p\u003e\n\u003ch4 id=\"optional-2-claude-code-config-npm-package-for-router-customization\"\u003eOptional 2: claude-code-config npm package for router customization\u003c/h4\u003e\n\u003cp\u003eclaude-code-router aims for customizing different backend models for Claude Code. The dashscope team also provide a convenient config npm extension, namely claude-code-config, that provides default configuration for claude-code-router with DashScope support.\nRun installation:\u003c/p\u003e\n\u003cpre\u003e\u003ccode class=\"language-bash\"\u003enpm install -g @musistudio/claude-code-router\nnpm install -g @dashscope-js/claude-code-config\n\u003c/code\u003e\u003c/pre\u003e\n\u003cp\u003eand then run configuration:\u003c/p\u003e\n\u003cpre\u003e\u003ccode class=\"language-bash\"\u003eccr-dashscope\n\u003c/code\u003e\u003c/pre\u003e\n\u003cp\u003eThe command will automatically generate the config json files and plugin directories for ccr. (You could also manually adjust these under ~/.claude-code-router/config.json and ~/.claude-code-router/plugins/ )\nStart using claude code via ccr:\u003c/p\u003e\n\u003cpre\u003e\u003ccode class=\"language-bash\"\u003eccr code\n\u003c/code\u003e\u003c/pre\u003e\n\u003ch3 id=\"cline\"\u003eCline\u003c/h3\u003e\n\u003cp\u003eConfigure the Qwen3-Coder-480B-A35B-Instruct to cline\n‒ Go to the Cline configuration settings\n‒ For API Provider, select 'OpenAI Compatible'\n‒ For the OpenAI Compatible API Key, enter the key obtained from Dashscope\n‒ Check 'Use custom base URL' and enter: \u003ccode\u003ehttps://dashscope-intl.aliyuncs.com/compatible-mode/v1\u003c/code\u003e\n‒ Enter \u003ccode\u003eqwen3-coder-plus\u003c/code\u003e\u003c/p\u003e\n\u003cvideo width=\"100%\" muted controls=\"1\"\u003e\n \u003csource src=\"https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen3-Coder/qwen3_coder_plus_with_cline.mp4\" type=\"video/mp4\"\u003e\n\u003c/video\u003e\n\u003ch2 id=\"use-cases\"\u003eUse Cases\u003c/h2\u003e\n\u003ch2 id=\"api\"\u003eAPI\u003c/h2\u003e\n\u003cp\u003eYou can directly access the API of Qwen3-Coder through \u003ca href=\"https://modelstudio.console.alibabacloud.com/\"\u003eAlibaba Cloud Model Studio\u003c/a\u003e. Here is a demonstration of how to use this model with the Qwen API.\u003c/p\u003e\n\u003cpre\u003e\u003ccode class=\"language-python\"\u003eimport os\nfrom openai import OpenAI\n\n# Create client - using intl URL for users outside of China\n# If you are in mainland China, use the following URL:\n# \"https://dashscope.aliyuncs.com/compatible-mode/v1\"\nclient = OpenAI(\n api_key=os.getenv(\"DASHSCOPE_API_KEY\"),\n base_url=\"https://dashscope-intl.aliyuncs.com/compatible-mode/v1\",\n)\n\nprompt = \"Help me create a web page for an online bookstore.\"\n\n\n# Send request to qwen3-coder-plus model\ncompletion = client.chat.completions.create(\n model=\"qwen3-coder-plus\",\n messages=[\n {\"role\": \"system\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": prompt}\n ],\n)\n\n# Print the response\nprint(completion.choices[0].message.content.strip())\n\u003c/code\u003e\u003c/pre\u003e\n\u003ch2 id=\"further-work\"\u003eFurther Work\u003c/h2\u003e\n\u003cp\u003eWe are still actively working to improve the performance of our Coding Agent, aiming for it to take on more complex and tedious tasks in software engineering, thereby freeing up human productivity. More model sizes of Qwen3-Coder are on the way, delivering strong performance while reducing deployment costs. Additionally, we are actively exploring whether the Coding Agent can achieve self-improvement—an exciting and inspiring direction.\u003c/p\u003e"])</script><script>self.__next_f.push([1,"7:[\"$\",\"main\",null,{\"children\":[\"$\",\"article\",null,{\"className\":\"blog-article\",\"data-upstream\":\"\",\"children\":[[\"$\",\"$L5\",null,{\"className\":\"blog-back\",\"href\":\"/blog\",\"children\":\"← Blog\"}],[\"$\",\"div\",null,{\"className\":\"blog-post-meta\",\"children\":[\"July 21, 2025\",\" \",\"·\",\" \",5,\" min read\"]}],[\"$\",\"h1\",null,{\"className\":\"blog-post-title\",\"children\":\"Qwen3-Coder: Agentic Coding in the World\"}],[\"$\",\"p\",null,{\"className\":\"blog-post-lede\",\"children\":\"Today, we're announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we're excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports t\"}],[\"$\",\"div\",null,{\"className\":\"blog-prose\",\"dangerouslySetInnerHTML\":{\"__html\":\"$14\"}}]]}]}]\n"])</script><script>self.__next_f.push([1,"10:[[\"$\",\"meta\",\"0\",{\"charSet\":\"utf-8\"}],[\"$\",\"meta\",\"1\",{\"name\":\"viewport\",\"content\":\"width=device-width, initial-scale=1\"}]]\nc:null\n"])</script><script>self.__next_f.push([1,"e:{\"metadata\":[[\"$\",\"title\",\"0\",{\"children\":\"Qwen3-Coder: Agentic Coding in the World — Zen Blog\"}],[\"$\",\"meta\",\"1\",{\"name\":\"description\",\"content\":\"Today, we're announcing Qwen3-Coder, our most agentic code model to date. Qwen3-Coder is available in multiple sizes, but we're excited to introduce its most powerful variant first: Qwen3-Coder-480B-A35B-Instruct — a 480B-parameter Mixture-of-Experts model with 35B active parameters which supports t\"}],[\"$\",\"meta\",\"2\",{\"name\":\"keywords\",\"content\":\"AI, LLM, Agentic AI, Code Generation, Zen Coder, Multimodal, Open Source, Machine Learning\"}],[\"$\",\"meta\",\"3\",{\"name\":\"data-upstream\",\"content\":\"true\"}]],\"error\":null,\"digest\":\"$undefined\"}\n"])</script><script>self.__next_f.push([1,"13:\"$e:metadata\"\n"])</script></body></html>