Macaron V1 Venti

MindlabMCP Tool CallReasoning

mindlab/macaron-v1-ventiOpen Weights

GLM-5.2-based Mixture-of-LoRA model with specialists for chat, personal agents, coding, and generative UI

Benchmark Pricing$0.82 / 1M in$2.48 / 1M out$0.17 cache read

Context: 1,048,576 tokens•Max Output: 131,072 tokens•Released: 2026-07-21

TECHNICAL SPECIFICATIONS

Context Window1,048,5761M tokens

Max Output131,072131.1K tokens

LicenseMITSelf-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Macaron V1 Venti natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 1,048,576 tokens, this model can handle extremely large MCP resource manifests, complete database schemas, and multiple active server tool definitions simultaneously without degradation.

API CALL INVOCATION EXAMPLE

// Example: Calling Macaron V1 Venti via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MINDLAB_API_KEY,
});

const response = await client.chat.completions.create({
  model: "mindlab/macaron-v1-venti",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);