Qwen: Qwen3 VL 235B A22B Instruct
qwen/qwen3-vl-235b-a22b-instruct
Access Qwen3 VL 235B A22B Instruct 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-vl-235b-a22b-instruct"
}).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-vl-235b-a22b-instruct"
}).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-vl-235b-a22b-instruct",
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-vl-235b-a22b-instruct",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
Qwen3 VL 235B A22B Instruct is Alibaba's flagship vision-language model, a mixture-of-experts architecture with 235 billion total parameters and 22 billion active per token, served through Alibaba's API.
It's built for visual coding (generating Draw.io, HTML, and CSS from screenshots or mockups), spatial reasoning about object positions and occlusion, and GUI/PC navigation as a visual agent. OCR covers 32 languages, including rare and ancient scripts, and holds up on low-light, blurred, or tilted text.
The model natively handles 256K tokens of interleaved text, image, and video, extendable to 1M tokens, and Alibaba reports near-full accuracy retention at that length, enough for hours-long video with second-level indexing. On OmniDocBench it scores 88.9 overall for document parsing.
It fits developers building document-processing pipelines, coding-from-screenshot tools, or agents that need to watch and reason over long video.
Context Window 131K
tokens
Max Output 33K
tokens
Input Cost $0.4
per million tokens
Output Cost $1.6
per million tokens
Input text, image
modalities
Tool Use Yes
Release Date Sep 23, 2025
Model Playground
Try Qwen3 VL 235B A22B Instruct instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Qwen3 VL 235B A22B Instruct performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 71.2% |
| Humanity's Last Exam Cross-domain reasoning | 6.6% |
| LiveCodeBench Recent coding problems | 59.4% |
| SciCode Scientific programming | 35.9% |
| AIME 2025 Advanced math exam | 70.7% |
| IFBench Instruction following | 42.7% |
| LCR Long-context reasoning | 32.0% |
| Terminal-Bench Hard Agentic terminal tasks | 6.8% |
| τ²-Bench Tool use / agents | 35.1% |
Scores sourced from Artificial Analysis.
Find other Qwen models →
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 VL 235B A22B Instruct 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 VL 235B A22B Instruct 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 | $0.4 |
| Output | $1.6 |
Qwen3 VL 235B A22B Instruct was created by Qwen and released on Sep 23, 2025.
Qwen3 VL 235B A22B Instruct supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.
Qwen3 VL 235B A22B Instruct can generate up to 33K tokens in a single response.
Qwen3 VL 235B A22B Instruct accepts the following input types: text, image. It produces: text.
Yes, Qwen3 VL 235B A22B Instruct supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Qwen3 VL 235B A22B Instruct scores 14.4 on the Artificial Analysis Intelligence Index, outperforming 45% of tracked models. On math, it scores 70.7 (outperforms 64% of models).
Yes — the Qwen3 VL 235B A22B Instruct 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 VL 235B A22B Instruct to your app without worrying about API keys or setup.
Read the Docs View Tutorials