Mind Lab: Macaron V1 Venti
mindai/macaron-v1-venti:free
Access Macaron V1 Venti from Mind Lab 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: "mindai/macaron-v1-venti:free"
}).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: "mindai/macaron-v1-venti:free"
}).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="mindai/macaron-v1-venti:free",
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": "mindai/macaron-v1-venti:free",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
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
Model Playground
Try Macaron V1 Venti instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Macaron V1 Venti by Mind Lab 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 Macaron V1 Venti 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 |
| Output | $0 |
Macaron V1 Venti supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,097 pages of text.
Macaron V1 Venti can generate up to 131K tokens in a single response.
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 Macaron V1 Venti to your app without worrying about API keys or setup.
Read the Docs View Tutorials