weckr

AI cost intelligence
for SaaS founders.

See cost, latency, and per-user margin for every LLM call — without adding latency to your app. Wrap any OpenAI, Anthropic, or Gemini client. Logs are fire-and-forget.

Open dashboard →View source
Drop-in
import { Weckr } from '@weckr/sdk';
import OpenAI from 'openai';

const wk = new Weckr({
  apiKey: 'wk_…',
  plans: { free: 0, pro: 29 },
});

await wk.chat(openai, {
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hi' }],
  userId: 'u_123', plan: 'pro',
});
Zero added latency

Logs fire after your LLM call returns. Failures don't bubble to your code.

Per-user margin

See exactly which users cost more than they pay. Plan revenue minus AI cost.

Provider-agnostic

OpenAI, Anthropic, Gemini — same SDK, same dashboard, same units.