Qwen: Qwen3.5-Omni Flash
qwen/qwen3.5-omni-flash
Access Qwen3.5-Omni Flash 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-omni-flash"
}).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-omni-flash"
}).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-omni-flash",
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-omni-flash",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
Qwen3.5-Omni Flash is the fast, cost-efficient tier of Alibaba's Qwen3.5-Omni family, a natively multimodal model that takes text, images, video, and audio as input in a single end-to-end architecture and returns text.
Both Flash and Plus share a Thinker-Talker design built on a Hybrid-Attention Mixture-of-Experts architecture, an upgrade over the prior Qwen3-Omni generation, with an ARIA module aligning text and speech tokens for streaming synthesis; this API route returns text only.
Alibaba's technical report shows Flash trading accuracy for speed against Plus: 79.9 vs 85.9 on MMLU-Pro, 81.9 vs 86.8 on MLVU video understanding, and a higher LibriSpeech word error rate (1.30-2.43 vs 1.11-2.23), while answering faster with a first-packet audio latency of 235ms versus 435ms.
With a 48K token context, tool calling, and $0.40/$2.20 per million input/output tokens, it fits voice assistants, live video analysis, and high-volume multimodal apps where latency and cost matter more than peak accuracy.
Context Window 49K
tokens
Max Output 16K
tokens
Input Cost $0.4
per million tokens
Output Cost $2.2
per million tokens
Input text, image, video, audio
modalities
Tool Use Yes
Release Date Mar 15, 2026
Output Speed 236
tokens / sec
Latency 0.94s
time to first token
Model Playground
Try Qwen3.5-Omni Flash instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Qwen3.5-Omni Flash performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 74.2% |
| Humanity's Last Exam Cross-domain reasoning | 7.6% |
| SciCode Scientific programming | 25.5% |
| IFBench Instruction following | 38.0% |
| LCR Long-context reasoning | 48.7% |
| Terminal-Bench Hard Agentic terminal tasks | 8.3% |
| τ²-Bench Tool use / agents | 84.5% |
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 Qwen3.5-Omni Flash 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-Omni Flash 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 | $2.2 |
Qwen3.5-Omni Flash was created by Qwen and released on Mar 15, 2026.
Qwen3.5-Omni Flash supports a context window of 49K tokens. For reference, that is roughly equivalent to 98 pages of text.
Qwen3.5-Omni Flash can generate up to 16K tokens in a single response.
Qwen3.5-Omni Flash accepts the following input types: text, image, video, audio. It produces: text.
Yes, Qwen3.5-Omni Flash supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Qwen3.5-Omni Flash scores 19.2 on the Artificial Analysis Intelligence Index, outperforming 54% of tracked models.
Yes — the Qwen3.5-Omni Flash 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-Omni Flash to your app without worrying about API keys or setup.
Read the Docs View Tutorials