Macaron V1 Venti is Mind Lab's flagship agent model, built as a Mixture-of-LoRA rather than a conventional monolith. A 744 billion parameter base carries four 1 billion parameter LoRA specialists, and an L0 router selects the specialist that suits each incoming request, so the model shifts behaviour per task instead of averaging across all of them. It is the first model post-trained on GLM-5.2, using a long-context post-training method the lab calls LongStraw that reaches context lengths of up to 2 million tokens. Mind Lab reports 87.6 on TerminalBench 2.1 and 87.8 on UI4ABench, and the design targets continual learning and model collaboration, which points it at long-horizon agent work, terminal use, and interactive interface generation.
Macaron V1 Venti runs on 1 route through the Opper gateway. Compare residency, ZDR, and training posture at a glance — full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| US | Enterprise | No | $1.50 | $4.50 |
Macaron V1 Venti runs on a single route through the Opper gateway today, so its availability is that provider's availability.
Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.
Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.
Each route hosting Macaron V1 Venti has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Call Macaron V1 Venti through the Opper gateway with one API key. Let your coding agent set it up, or call it directly — Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "novita/mindai/macaron-v1-venti",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
