Qwen: Qwen3-Omni Flash (2025-09-15)
This model is no longer available.Add AI to your application with Puter.js.
Explore Other Models
Model Card
Qwen3-Omni Flash (2025-09-15) is a dated snapshot of Alibaba's fast, cost-efficient omni-modal model, capturing its state as first released alongside the broader Qwen3-Omni family on September 22, 2025.
It ingests text, images, audio, and video in a single end-to-end architecture and returns text, with low-latency streaming support suited to voice assistants and live audio/video analysis. The Flash tier trades peak capability for speed and throughput, with a 65K context window and 16K output limit tuned for high-volume, cost-sensitive inference.
Pinning to this snapshot locks in behavior from before Alibaba's December 2025 update, which added smoother multi-turn audio/video conversation handling and system-prompt personality customization. Choose this ID when reproducible output matters more than picking up the newest Flash improvements.
Context Window 66K
tokens
Max Output 16K
tokens
Input Cost $0.43
per million tokens
Output Cost $1.66
per million tokens
Input text, image, audio, video
modalities
Tool Use Yes
Release Date Sep 15, 2025
Code Example
Add AI to your app with the Puter.js AI API, no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").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").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
More AI Models From Qwen
Qwen3.7 Plus
Qwen3.7 Plus is Alibaba's multimodal agent model, released in June 2026, combining vision-language understanding with full agentic capabilities across a 1 million-token context window. Unlike the text-only Qwen3.7 Max, Plus ingests images and video alongside text, processed through early-fusion training so vision and language are jointly understood from the first layer. This enables GUI grounding — the model can interpret screenshots and issue precise on-screen actions — scoring 79.0 on ScreenSpot Pro, placing it alongside Claude Computer Use and OpenAI Operator in the GUI automation tier. Beyond vision, it adds deep reasoning, self-programming, tool invocation, and autonomous iteration: the model writes and tests code, calls external APIs, and loops until the task is done. On the Artificial Analysis Intelligence Index it scores 53. Choose it over Qwen3.7 Max when your workflow requires image or video inputs, browser/desktop automation, or end-to-end agentic pipelines that combine seeing, reasoning, and doing.
ChatQwen3.7 Max
Qwen3.7 Max is Alibaba's flagship proprietary reasoning model, released in May 2026, built for long-horizon agentic workloads with a 1 million-token context window and a chain-of-thought reasoning architecture. It is purpose-built for complex, multi-step autonomous tasks. Alibaba demonstrated the model running for 35 hours without degradation, executing over 1,000 tool calls in a single session — making it a strong candidate for coding agents, automated pipelines, and deep document analysis. On benchmarks, it ranks 13th globally on LM Arena's text leaderboard and scores 56.6 on the Artificial Analysis Intelligence Index, making it the highest-ranked Chinese model on that index. It posted 90.2 on Arena-Hard v2 and 72.5 on SWE-Bench Verified. Qwen3.7 Max supports the Anthropic API protocol natively, so it integrates cleanly with tooling like Claude Code. It is well-suited for developers building coding assistants, research agents, or any API use case requiring extended reasoning over large contexts.
ChatQwen3.6 Flash
Qwen3.6 Flash is the speed-optimized tier of Alibaba's Qwen3.6 model family, designed for high-throughput, low-latency inference pipelines. It sits alongside Qwen3.6 Max Preview, Plus, and 35B-A3B in the product lineup, targeting use cases where fast response times matter more than peak benchmark scores. Like other Qwen3.6 models, it builds on a hybrid architecture combining linear attention with sparse mixture-of-experts routing. It is best suited for high-volume production workloads such as classification, extraction, summarization, and lightweight agent tasks where latency and cost efficiency are the primary constraints.
Frequently Asked Questions
Qwen3-Omni Flash (2025-09-15) is no longer available through Puter.js. Explore other AI models for alternatives.
| Price per 1M tokens | |
|---|---|
| Input | $0.43 |
| Output | $1.66 |
Qwen3-Omni Flash (2025-09-15) was created by Qwen and released on Sep 15, 2025.
Qwen3-Omni Flash (2025-09-15) supports a context window of 66K tokens. For reference, that is roughly equivalent to 131 pages of text.
Qwen3-Omni Flash (2025-09-15) can generate up to 16K tokens in a single response.
Qwen3-Omni Flash (2025-09-15) accepts the following input types: text, image, audio, video. It produces: text.
Yes, Qwen3-Omni Flash (2025-09-15) 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-Omni Flash (2025-09-15) 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 AI to your application without worrying about API keys or setup.
Explore Models View Tutorials