is-it-spam

LLM-based spam classifier. Works with any OpenAI-compatible API.

Install

npm i is-it-spam

Usage

import { createClassifier } from "is-it-spam";

const isSpam = createClassifier({
  apiKey: process.env.OPENROUTER_API_KEY!,
  zdr: true
});

if (await isSpam("Need a quote for your services")) {
  // spam
}

// or get details
const result = await isSpam.details("Need a quote");
// { isSpam: false, confidence: 0.95, reason: "..." }

Options

| Option | Type | Default | Description | |--------|------|---------|-------------| | apiKey | string | required | API key | | model | string | openai/gpt-5.4-nano | Model to use | | baseUrl | string | OpenRouter | API endpoint | | zdr | boolean | false | Zero Data Retention |

Providers

Works with any OpenAI-compatible API:

// OpenRouter (default)
const isSpam = createClassifier({ apiKey: process.env.OPENROUTER_API_KEY! });

// OpenAI
const isSpam = createClassifier({
  apiKey: process.env.OPENAI_API_KEY!,
  baseUrl: "https://api.openai.com/v1/chat/completions",
  model: "gpt-4o-mini",
});

// Local LLM
const isSpam = createClassifier({
  apiKey: "not-needed",
  baseUrl: "http://localhost:11434/v1/chat/completions",
  model: "llama3",
});

Fail-Safe

Returns false (legitimate) if the API fails, so you never block real customers.

Cost

~$0.0002 per check. 10,000 checks = ~$2.

License

MIT