Regolo.ai built Brick Complexity Pro as the hosted endpoint of the complexity stage in Brick, its open-source semantic router. Instead of generating answers, the model reads an incoming prompt and returns a difficulty grade of easy, medium, or hard, judging semantic demands rather than length, so a short legal-review request can score harder than a long how-to question. That verdict lets routing pipelines choose a model tier before any generation happens, reserving heavyweight models for genuinely hard queries and letting lighter ones absorb the rest. With structured output and latency low enough to sit inline in front of every call, it slots naturally into cost-aware cascades and automatic model selection.
Brick Complexity Pro 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 |
|---|---|---|---|---|---|
| EU | Zero data retention | No | $0.12 | $0.46 |
Each route hosting Brick Complexity Pro has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. EU; DPA available.
Call Brick Complexity Pro 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: "regolo/brick-complexity-pro",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
