Mind Lab: Macaron V1 Venti

This model is no longer available.

Add AI to your application with Puter.js.

Explore Other Models

Model Card

Macaron V1 Venti is a 748-billion-parameter Mixture-of-LoRA model from Mind Lab, pairing a 744B-parameter base model, the first post-trained on Zhipu's GLM-5.2, with four 1B-parameter LoRA specialists for chat, agent tasks, coding, and generative UI; an L0 router picks a specialist per request.

It supports a 1M-token context window; Mind Lab's LongStraw training stack enables post-training and reinforcement learning at context lengths up to 2 million tokens.

Mind Lab reports Macaron V1 leading GPT-5.5, Claude Opus 4.8, Gemini 3.1 Pro, Qwen 3.7 Max, and Minimax M3 on ChatBench (58.3), LivingBench (64.0), PinchBench (94.0), TerminalBench 2.1 (87.6), and UI4ABench (87.8). On coding benchmarks like SWE Verified and DeepSWE, Mind Lab says it sits close to, rather than ahead of, the frontier models. These figures are vendor-reported, not independently verified.

It targets personal-intelligence agents, long-horizon tool use, coding workflows, and code-native Generative UI, offered here free of charge.

Context Window 1M

tokens

Max Output 131K

tokens

Input Cost $0

per million tokens

Output Cost $0

per million tokens

Release Date N/A

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>

Frequently Asked Questions

How do I use Macaron V1 Venti?

Macaron V1 Venti is no longer available through Puter.js. Explore other AI models for alternatives.

What is the pricing for Macaron V1 Venti?

Macaron V1 Venti costs $0 per 1M input tokens and $0 per 1M output tokens.

	Price per 1M tokens
Input	$0
Output	$0

What is the context window of Macaron V1 Venti?

Macaron V1 Venti supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,097 pages of text.

What is the max output length of Macaron V1 Venti?

Macaron V1 Venti can generate up to 131K tokens in a single response.

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

Yes — the Macaron V1 Venti 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