I built an LLM API cost tracker after a $200 surprise OpenAI bill
I built an LLM API cost tracker – here's why
I got a $200 surprise OpenAI bill last month and had no idea which prompt caused it. So I built LLMWatch.
It's a proxy that sits between your app and OpenAI. Change one line of code and every request is logged with cost, latency, and token usage.
// Before
baseURL: "https://api.openai.com"
// After
baseURL: "https://llmwatch-rho.vercel.app/api/proxy"
Features:
- Real-time cost tracking
- Monthly budget alerts (email when you hit 80%)
- Free tier: 1,000 requests/month
- Pro: $20/month unlimited
Would love feedback from anyone building with LLMs!
