nerovai

Real-time AI spend tracking for developers. Track every OpenAI, Anthropic, Google, Mistral, DeepSeek, Groq, Kimi, Cohere, and Perplexity call — automatically.

Install

npm install nerovai

Quick start

const { track } = require('nerovai')
const OpenAI = require('openai')

const openai = new OpenAI()

// Wrap your existing call — response is returned untouched
const response = await track(
  openai.chat.completions.create({
    model: 'gpt-4o',
    messages: [{ role: 'user', content: 'Hello' }]
  })
)

Set your API key (get it from nerovai.com/app):

NEROVAI_API_KEY=nuerova_xxxx node your-app.js

Options

await track(operation, {
  project_id: 'your-project-id',   // organize by project
  endpoint_name: '/chat',           // tag by route
  metadata: { userId: '123' },      // any extra data
  cost: 0.005,                      // override auto-calculated cost
  provider: 'openai',               // override auto-detected provider
})

Environment variables

| Variable | Description | |----------|-------------| | NEROVAI_API_KEY | Your API key from nerovai.com/app | | NEROVAI_ENDPOINT | Custom endpoint (default: https://api.nerovai.com/api/logs) |

Supported providers

OpenAI · Anthropic · Google · Mistral · DeepSeek · Groq · Kimi · Cohere · Perplexity

Cost is calculated automatically from the response's token usage for all supported models.

Links

• Dashboard
• Docs
• nerovai.com