Qwen: Qwen3.5 397B A17B
qwen/qwen3.5-397b-a17b
Access Qwen3.5 397B A17B 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/qwen3.5-397b-a17b"
}).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/qwen3.5-397b-a17b"
}).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/qwen3.5-397b-a17b",
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/qwen3.5-397b-a17b",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
Qwen3.5-397B-A17B is an open-weight native vision-language model from Alibaba's Qwen team, released in February 2026. It uses a hybrid architecture combining Gated Delta Networks (linear attention) with a sparse mixture-of-experts design, totaling 397 billion parameters but activating only 17 billion per forward pass for efficient inference. The model delivers strong performance across reasoning, coding, agent tasks, and multimodal understanding, competing with frontier models like GPT-5.2, Claude 4.5 Opus, and Gemini-3 Pro. It supports 201 languages and dialects and features a 250k-token vocabulary. Its decoding throughput is reported at 8.6x that of Qwen3-Max under a 32k context length.
Context Window 262K
tokens
Max Output 66K
tokens
Input Cost $0.6
per million tokens
Output Cost $3.6
per million tokens
Input text, image, video, audio
modalities
Tool Use Yes
Release Date Feb 15, 2026
Output Speed 91
tokens / sec
Latency 1.43s
time to first token
Model Playground
Try Qwen3.5 397B A17B instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Qwen3.5 397B A17B performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 89.3% |
| Humanity's Last Exam Cross-domain reasoning | 29.0% |
| SciCode Scientific programming | 42.0% |
| IFBench Instruction following | 78.8% |
| LCR Long-context reasoning | 72.7% |
| Terminal-Bench Hard Agentic terminal tasks | 40.9% |
| τ²-Bench Tool use / agents | 95.6% |
Scores sourced from Artificial Analysis.
Find other Qwen models →
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.
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.
ChatQwen3.8 Max
Qwen3.8 Max is Alibaba's flagship large language model, released August 3, 2026 as the most capable model in the Qwen family to date. It uses a mixture-of-experts architecture with 2.4 trillion total parameters and about 95 billion active per request, and accepts text, image, and video input with a context window of up to 1 million tokens. Alibaba positions it for coding and long-horizon agentic work: in testing the model ran autonomously for over 10 days building a self-evolving software harness. Reported benchmarks include 93.0 on PaperBench, 82.8 on IFBench, 86.6 on Terminal-Bench 2.1, and 86.1 on OSWorld-Verified, ahead of Claude Opus 4.8 on several coding and agent tasks and roughly matching Claude Fable 5 and GPT-5.6 Sol, though it trails both on some evaluations. On the Arena.AI leaderboard it ranks as the top Chinese model for text tasks. Alibaba plans to open-source the weights on Hugging Face and ModelScope.
Frequently Asked Questions
You can access Qwen3.5 397B A17B 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 Qwen3.5 397B A17B 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 | $0.6 |
| Output | $3.6 |
Qwen3.5 397B A17B was created by Qwen and released on Feb 15, 2026.
Qwen3.5 397B A17B supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Qwen3.5 397B A17B can generate up to 66K tokens in a single response.
Qwen3.5 397B A17B accepts the following input types: text, image, video, audio. It produces: text.
Yes, Qwen3.5 397B A17B supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Qwen3.5 397B A17B scores 34.3 on the Artificial Analysis Intelligence Index, outperforming 78% of tracked models. On coding, it scores 48.2 (outperforms 60% of models).
Yes — the Qwen3.5 397B A17B 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 Qwen3.5 397B A17B to your app without worrying about API keys or setup.
Read the Docs View Tutorials