Stop manually logging your AI API calls — one-line auto-logging for OpenAI and Anthropic

Every time you call an AI API, you're spending money. But unless you're checking the dashboard after each session, you have no idea which project or model is driving the bill.

I solved this by wrapping my AI clients with a one-line middleware that logs every call automatically.

The problem with manual logging

AICostTracker lets you run aicost log myapp gpt-4o 1500 800 to record a call. Useful — but nobody does this consistently. You forget, you're in flow, you'll do it later.

The logs end up patchy and the summary is useless.

Auto-logging with track()

In v0.1.2, I added a track() function that wraps your OpenAI or Anthropic client:

npm install @ozperium/aicost-tracker

import OpenAI from 'openai';
import { track } from '@ozperium/aicost-tracker';

const openai = track(new OpenAI(), { project: 'myapp' });

// From here, every call is logged automatically
const response = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Summarize this doc' }]
});

That's it. No changes to your existing code beyond the wrap.

It works the same way with Anthropic:

import Anthropic from '@anthropic-ai/sdk';
import { track } from '@ozperium/aicost-tracker';

const anthropic = track(new Anthropic(), { project: 'summarizer' });
const response = await anthropic.messages.create({ model: 'claude-3-5-sonnet-20241022', ... });

What gets logged

After a few sessions:

aicost summary

  AI Cost Tracker — Summary
  ══════════════════════════════════════════════════
  Total cost:       $1.2847
  Input tokens:     124,000
  Output tokens:    67,500

  By Project:
  ──────────────────────────────────────────────────
  myapp                $    0.9102  31 calls
  summarizer           $    0.3745  12 calls

  By Model:
  ──────────────────────────────────────────────────
  gpt-4o               $    0.9102  31 calls
  claude-3-5-sonnet    $    0.3745  12 calls

How it works

track() patches client.chat.completions.create (OpenAI) or client.messages.create (Anthropic) to intercept the response, extract usage from the usage field, and call logUsage() before returning. It's a thin synchronous wrapper — zero added latency.

If logging fails for any reason, the error is swallowed silently. Your API call always gets its response.

Per-project breakdown

The { project: 'myapp' } option lets you tag every call with a project name. If you're running multiple agents or tools in the same codebase, give each its own project tag:

const researchAgent = track(new OpenAI(), { project: 'research' });
const summaryAgent = track(new OpenAI(), { project: 'summary' });

Then aicost summary shows the breakdown by project automatically.

---

GitHub: https://github.com/Ozperium/aicost-tracker

Also: AgentSpec for testing AI agent behavior, quota for monitoring rate limits.

Comments

[Alex Shev]

Automatic logging is one of those features that feels small until the first weird model failure. Having the request shape, model, latency, token use, and response metadata in one place saves a lot of guesswork.

The main thing I would guard is accidental capture of sensitive prompt/tool data. For AI logs, the default should be useful observability with aggressive redaction, not a perfect transcript of everything the app saw.

[Mafrito]

I fully agree with your approach. Logging every single operation is a surefire way to leak personally identifiable information (PII) or trade secrets into the logs. Observability should provide insight into how the system works, not collect confidential information.
Today, users are increasingly spinning the reels on their smartphones, demanding maximum flexibility and mobility from the service. Mobile-optimized Fast Payout Casinos animeflix.city/ let you request payouts with a single click via Apple Pay, Google Pay, or crypto wallets. Manage your finances on the go and claim your winnings immediately after finishing your gaming session.