Ship a Full-Stack App with One Prompt

Copy this prompt into your AI coding agent, or open it in one below.

Give this to your AI Create a to-do list app using Puter.js

Coding manually? see the guide

Qwen

Qwen: Qwen3 235B-A22B Instruct 2507

qwen/qwen3-235b-a22b-instruct-2507

Access Qwen3 235B-A22B Instruct 2507 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/qwen3-235b-a22b-instruct-2507"
}).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/qwen3-235b-a22b-instruct-2507"
        }).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/qwen3-235b-a22b-instruct-2507",
    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/qwen3-235b-a22b-instruct-2507",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Qwen3 235B-A22B Instruct 2507 is Alibaba's non-thinking-mode update to its 235B-parameter Mixture-of-Experts flagship, activating 22B parameters per token and served with a 262,144-token context window.

Against the original Qwen3-235B-A22B, Alibaba reports gains from 75.2 to 83.0 on MMLU-Pro, 24.7 to 70.3 on AIME25, and 52.0 to 79.2 on Arena-Hard v2. On GPQA it scores 77.5, ahead of GPT-4o's 66.9.

It supports tool calling and is built for instruction following, coding, math, science, and multilingual tasks. Unlike the paired Thinking-2507 variant, it answers directly without a visible reasoning trace, trading step-by-step chain-of-thought for lower latency and fewer output tokens per request, useful for production workloads where response speed matters more than showing intermediate reasoning.

Context Window 262K

tokens

Max Output 33K

tokens

Input Cost $0.23

per million tokens

Output Cost $0.92

per million tokens

Input text

modalities

Tool Use Yes

 

Knowledge Cutoff Apr 2025

 

Release Date Jul 2025

 

Model Playground

Try Qwen3 235B-A22B Instruct 2507 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat qwen/qwen3-235b-a22b-instruct-2507
Qwen
Chat with Qwen3 235B-A22B Instruct 2507
Powered by Puter.js

Benchmarks

How Qwen3 235B-A22B Instruct 2507 performs on standard evaluations.

Artificial Analysis
Intelligence Index
18.4
Better than 53% of tracked models
Artificial Analysis
Math Index
71.7
Better than 65% of tracked models
BenchmarkScore
GPQA Diamond Graduate-level science Q&A
75.3%
Humanity's Last Exam Cross-domain reasoning
11.1%
LiveCodeBench Recent coding problems
52.4%
SciCode Scientific programming
36.0%
MATH-500 Competition math
98.0%
AIME 2024 Advanced math exam
71.7%
AIME 2025 Advanced math exam
71.7%
IFBench Instruction following
46.1%
LCR Long-context reasoning
33.0%
Terminal-Bench Hard Agentic terminal tasks
15.2%
τ²-Bench Tool use / agents
33.3%

Scores sourced from Artificial Analysis.

Find other Qwen models

Chat

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.

Chat

Qwen3.8 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.

Chat

Qwen3.8 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

How do I use Qwen3 235B-A22B Instruct 2507?

You can access Qwen3 235B-A22B Instruct 2507 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 Qwen3 235B-A22B Instruct 2507 free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Qwen3 235B-A22B Instruct 2507 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 Qwen3 235B-A22B Instruct 2507?
Qwen3 235B-A22B Instruct 2507 costs $0.23 per 1M input tokens and $0.92 per 1M output tokens.
Price per 1M tokens
Input$0.23
Output$0.92
Who created Qwen3 235B-A22B Instruct 2507?

Qwen3 235B-A22B Instruct 2507 was created by Qwen and released on Jul 2025.

What is the context window of Qwen3 235B-A22B Instruct 2507?

Qwen3 235B-A22B Instruct 2507 supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.

What is the max output length of Qwen3 235B-A22B Instruct 2507?

Qwen3 235B-A22B Instruct 2507 can generate up to 33K tokens in a single response.

What is the knowledge cutoff of Qwen3 235B-A22B Instruct 2507?

Qwen3 235B-A22B Instruct 2507 has a knowledge cutoff date of Apr 2025. This means the model was trained on data available up to that date.

What types of input can Qwen3 235B-A22B Instruct 2507 process?

Qwen3 235B-A22B Instruct 2507 accepts the following input types: text. It produces: text.

Does Qwen3 235B-A22B Instruct 2507 support tool use (function calling)?

Yes, Qwen3 235B-A22B Instruct 2507 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.

How does Qwen3 235B-A22B Instruct 2507 perform on benchmarks?

Qwen3 235B-A22B Instruct 2507 scores 18.4 on the Artificial Analysis Intelligence Index, outperforming 53% of tracked models. On math, it scores 71.7 (outperforms 65% of models).

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

Yes — the Qwen3 235B-A22B Instruct 2507 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 235B-A22B Instruct 2507 to your app without worrying about API keys or setup.

Read the Docs View Tutorials