Two ways in.

SDK INTEGRATION

import { Cyphrex } from 'cyphrex';

const cyphrex = new Cyphrex({
  apiKey: 'cprx_live_...',
  agentId: '...'
});

// Step 1: check before every LLM call
const check = await cyphrex.check({
  actionType: 'http_call',
  url: 'api.openai.com/v1/chat'
});
if (!check.allowed) return;

// Step 2: your normal LLM call
const response = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages
});

// Step 3: automatic cost tracking
await cyphrex.check({
  actionType: 'llm_response',
  payload: response
});