Qwen: Qwen3 Max (2025-09-23)
qwen/qwen3-max-2025-09-23
Access Qwen3 Max (2025-09-23) 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/qwen3-max-2025-09-23"
}).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/qwen3-max-2025-09-23"
}).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/qwen3-max-2025-09-23",
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/qwen3-max-2025-09-23",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
Qwen3 Max (2025-09-23) is Alibaba's flagship proprietary large language model, a trillion-parameter-class Mixture-of-Experts system trained on 36 trillion tokens and offered only through the API rather than as open weights.
This snapshot marks Qwen's official, non-preview Qwen3 Max launch, following the earlier September 5 preview. Alibaba reported 72.5 on SWE-Bench Verified, 69.6 on Tau2-Bench Verified, 81.6 on AIME25, and 74.8 on LiveCodeBench v6, and the model reached the top three on the LMArena text leaderboard, ahead of GPT-5-Chat in that ranking.
It runs non-thinking, answering directly without a separate reasoning pass, which keeps latency down for coding assistants and tool-calling agents. Pinning to this dated snapshot instead of the general qwen3-max alias keeps behavior fixed for production use, ahead of the hybrid-thinking update Alibaba shipped in the January 2026 snapshot.
Context Window 262K
tokens
Max Output 66K
tokens
Input Cost $1.2
per million tokens
Output Cost $6
per million tokens
Input text
modalities
Tool Use Yes
Knowledge Cutoff Apr 2025
Release Date Sep 23, 2025
Model Playground
Try Qwen3 Max (2025-09-23) instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
More AI Models From Qwen
Qwen3.8 Flash
Qwen3.8 Flash is a multimodal model from Alibaba's Qwen team, released August 26, 2026, as the fast, lower-cost tier of the Qwen3.8 family alongside Qwen3.8 Max and Qwen3.8 27B. It uses a mixture-of-experts architecture with 125B total parameters and 6B active per token, an early preview of the architecture planned for Qwen4. It accepts text, image, and video input and returns text, with a 1,000,000 token context window and output capped at 128,000 tokens. The API supports tool calling, structured outputs via JSON schema, and prompt caching, with cached input billed at $0.016 per million tokens. Pricing is $0.14 per million input tokens and $0.42 per million output tokens, about one-twelfth the cost of Qwen3.8 Max. Alibaba says it was trained at roughly one-ninth the cost of Qwen3.7-Plus and reports higher scores on benchmarks including SWE-bench Pro and CoWorkBench, an agentic office-task benchmark.
ChatQwen3.8 27B
Qwen3.8 27B is a dense, open-weight multimodal model from Alibaba's Qwen team, released August 14, 2026 as a smaller member of the Qwen3.8 family alongside the flagship Qwen3.8 Max. It combines Gated DeltaNet linear attention with standard gated attention across 64 layers, giving a 27 billion parameter dense model a native 262K token context window, extendable to 1M tokens. It accepts text, image, and video input, including hour-scale video and STEM diagrams. Alibaba reports 61.7 on SWE-bench Pro and 73.0 on Terminal Bench 2.1, both improvements over the earlier Qwen3.6 27B, and 89.2 on GPQA Diamond. Released under Apache 2.0, it gives developers an open-weight alternative to Qwen3.8 Max for coding and agentic tasks, at a fraction of the parameter count.
ChatQwen3.8 2.4T A95B
Qwen3.8 2.4T A95B is Alibaba's open-weight release of its Qwen3.8 Max flagship, a sparse mixture-of-experts model with 2.4 trillion total parameters and 95 billion active per token, routed across 512 experts. It uses a hybrid attention design (Gated DeltaNet and Gated Attention layers) across 92 layers, with a native 262K context window and thinking mode enabled for every response. Alibaba reports 93.0 on PaperBench (ahead of GPT-5.6 Sol's 90.5), 92.6 on GPQA Diamond, 86.6 on Terminal-Bench 2.1, and 67.7 on SWE-bench Pro, positioning it for coding, research, and long-horizon agentic work. It gives developers access to Qwen-Max-class capability under open weights, useful for teams that want frontier-level coding and agentic performance without a closed API.
Frequently Asked Questions
You can access Qwen3 Max (2025-09-23) 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.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Qwen3 Max (2025-09-23) to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $1.2 |
| Output | $6 |
Qwen3 Max (2025-09-23) was created by Qwen and released on Sep 23, 2025.
Qwen3 Max (2025-09-23) supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Qwen3 Max (2025-09-23) can generate up to 66K tokens in a single response.
Qwen3 Max (2025-09-23) has a knowledge cutoff date of Apr 2025. This means the model was trained on data available up to that date.
Qwen3 Max (2025-09-23) accepts the following input types: text. It produces: text.
Yes, Qwen3 Max (2025-09-23) supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Yes — the Qwen3 Max (2025-09-23) 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 Qwen3 Max (2025-09-23) to your app without worrying about API keys or setup.
Read the Docs View Tutorials