Meituan: LongCat Flash Chat API

Access Meituan: LongCat Flash Chat from Meituan using Puter.js AI API.

Get Started

Model Card

LongCat Flash Chat is a 560B parameter Mixture-of-Experts model by Meituan that dynamically activates only 18-31B parameters per token for efficiency. It supports 128K context length and excels at agentic tasks including multi-step reasoning, tool use, and coding. Released under MIT license in September 2025, it achieves over 100 tokens per second inference speed.

Context Window

N/A

tokens

Max Output

131,072

tokens

Input Cost

$0.2

per million tokens

Output Cost

$0.8

per million tokens

API Usage Example

Add Meituan: LongCat Flash Chat to your app with just a few lines of code.
No API keys, no backend, no configuration required.

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "meituan/longcat-flash-chat"
        }).then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

View full documentation →

Get started with Puter.js

Add Meituan: LongCat Flash Chat to your app without worrying about API keys or setup.

Read the Docs View Tutorials