Meituan: LongCat Flash Chat

This model is no longer available.

Add AI to your application with Puter.js.

Explore Other Models

Model Card

LongCat Flash Chat is a 560-billion-parameter Mixture-of-Experts (MoE) language model developed by Meituan, dynamically activating roughly 27B parameters per token for an efficient balance of capability and cost.

As a non-thinking foundation model, it's optimized for conversational and agentic tasks, with particular strengths in tool use and multi-step interactions. It supports a 128K-token context window and delivers over 100 tokens per second at inference. On benchmarks, it scores 86.5 on ArenaHard-V2, 89.7 on MMLU, and 67.7 on τ²-Bench, performing competitively with models like DeepSeek-V3.1 and Kimi-K2 while activating fewer parameters.

A strong pick for developers building agentic workflows, coding assistants, or complex tool-calling pipelines where speed and efficiency matter.

Context Window 131K

tokens

Max Output 33K

tokens

Input Cost $0.2

per million tokens

Output Cost $0.8

per million tokens

Release Date Sep 1, 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 Meituan

Find other Meituan models →

Chat

LongCat 2.0

LongCat 2.0 is a 1.6-trillion-parameter Mixture-of-Experts (MoE) language model from Meituan, activating between roughly 33B and 56B parameters per token depending on query complexity. It supports a native 1-million-token context window through a custom LongCat Sparse Attention mechanism built for long-context workloads, and is tuned for agentic coding tasks such as whole-repository reasoning, multi-step terminal use, and cross-language migration. On SWE-bench Pro it scores 59.5, edging GPT-5.5's 58.6, and reaches 70.8 on Terminal-Bench 2.1 and 77.3 on SWE-bench Multilingual; Meituan reports overall performance comparable to Google's Gemini 3.1 Pro. A good fit for developers building coding agents or tools that need large context windows for whole-codebase reasoning.

Frequently Asked Questions

How do I use LongCat Flash Chat?

LongCat Flash Chat is no longer available through Puter.js. Explore other AI models for alternatives.

What is the pricing for LongCat Flash Chat?

LongCat Flash Chat costs $0.2 per 1M input tokens and $0.8 per 1M output tokens.

	Price per 1M tokens
Input	$0.2
Output	$0.8

Who created LongCat Flash Chat?

LongCat Flash Chat was created by Meituan and released on Sep 1, 2025.

What is the context window of LongCat Flash Chat?

LongCat Flash Chat supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.

What is the max output length of LongCat Flash Chat?

LongCat Flash Chat can generate up to 33K tokens in a single response.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the LongCat Flash Chat 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