API Cost Tracker 💰

Stop guessing your AI spend. Track costs per task, model, and project. Know your ROI.

The Problem

AI costs are invisible until the bill arrives.

What you see	What you don't see
Monthly API bill	Cost per task/project
"You used 2M tokens"	Which sessions cost most
Rate limit errors	Cost efficiency of each model

Real costs add up fast:

• Single coding session: $5-50
• Multi-agent system per day: $100s
• Monthly bill surprise: $500+

The Solution

TRACK    → Log every API call (model, tokens, cost, project)
ANALYZE  → Weekly review: top costs, model efficiency, trends
OPTIMIZE → Route tasks to cost-efficient models

Quick Start

1. Create cost-log.yaml

entries:
  - timestamp: 2026-04-27T03:00:00Z
    task: "Code review: auth module"
    model: claude-3-opus
    input_tokens: 8500
    output_tokens: 2200
    cost_usd: 0.68
    project: myapp-backend

2. Add to Your Agent

After every API call, log to cost-log.yaml:
timestamp, task, model, input_tokens, output_tokens, cost_usd, project

3. Analyze Weekly

Ask your agent:

"Analyze cost-log.yaml: top 5 expensive tasks, cost by model, weekly trend"

Pricing Reference (2026)

Model	Input ($/1M)	Output ($/1M)	Best For
Claude 3 Opus	$15	$75	Complex reasoning
Claude 3 Sonnet	$3	$15	General use
GPT-4 Turbo	$10	$30	Code, analysis
GPT-3.5 Turbo	$0.50	$1.50	Simple tasks

What You Get

• 📊 Visibility: Know exactly where your money goes
• 🎯 Attribution: Cost per project, not just total
• ⚡ Optimization: Data-driven model selection
• 🔮 Forecasting: Predict monthly spend before surprise

Anti-Patterns

❌ Bad	✅ Good
Check bill later	Log every session
Expensive model for simple tasks	Route by complexity
No project tags	Tag every entry

---

Every dollar saved is a dollar for more valuable AI tasks.

Install

# Claude Code
cp SKILL.md .claude/skills/api-cost-tracker/

# OpenClaw
cp SKILL.md ~/.openclaw/workspace/skills/api-cost-tracker/

# Cursor
cp SKILL.md .cursor/rules/api-cost-tracker.mdc

License

MIT — Use freely, attribute if you like.