Drex 2.0
Nace-ainace-ai/drex-v2.0Open Weights35B mixture-of-experts System One decision model with 3B active parameters, returning typed, calibrated probabilities over text or structured state without generating text
Benchmark Pricing$0.06 / 1M in$0.00 / 1M out
Context: 131,072 tokens•Max Output: 4,096 tokens•Released: 2026-10-06
TECHNICAL SPECIFICATIONS
Context Window131,072131.1K tokens
Max Output4,0964.1K tokens
LicenseNace.AI Open RAIL-MSelf-hostable
Input Modalities
Text
Function / Tool CallingNot Supported
Structured OutputsPrompt Based
MODEL CONTEXT PROTOCOL (MCP) READINESS
⚠ Drex 2.0 does not natively advertise tool-calling capabilities. When connecting to MCP servers, function calling must be handled via structured prompt injection.
MCP Context Window Recommendations
With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.
API CALL INVOCATION EXAMPLE
// Example: Calling Drex 2.0 via OpenAI SDK
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.NACE-AI_API_KEY,
});
const response = await client.chat.completions.create({
model: "nace-ai/drex-v2.0",
messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});
console.log(response.choices[0].message.content);PRICING BY PROVIDER
OpenRouternace-ai/drex-v2.0
$0.06 / $0.00
Rates in USD per 1M tokens. Rates synchronized from models.dev public catalog.
MODEL RESOURCES
More Models by Nace-ai
Alternative and family models from the same lab