ai-cost-auditor 0.1.0

Track AI API costs, token usage, and prompt quality across all providers

AI Cost Auditor

Track AI API costs, token usage, and prompt quality across all providers — Anthropic, OpenAI, Google, Mistral, and more.

Install

pip install ai-cost-auditor

With provider SDKs:

pip install "ai-cost-auditor[anthropic]"
pip install "ai-cost-auditor[openai]"
pip install "ai-cost-auditor[all]"

Quick Start

from ai_cost_auditor import CostTracker
import anthropic

tracker = CostTracker()
client  = tracker.wrap_anthropic(anthropic.Anthropic())

# Use exactly like the normal client — tracking is automatic
resp = client.messages.create(
    model="claude-sonnet-4-6",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Explain async/await in Python"}]
)

# View stats
stats = tracker.get_stats(days=7)
print(f"Cost: ${stats['period']['total_cost_usd']:.4f}")

# Generate HTML report with charts
tracker.generate_report("report.html")

Features

• Cost tracking — automatic pricing for 30+ models
• Token tracking — input/output tokens per call, by day/model/provider
• Prompt quality — 5-dimension scoring (clarity, specificity, context, structure, efficiency)
• HTML reports — interactive Chart.js charts: cost over time, provider breakdown, model usage
• Language-agnostic — works with any provider via manual tracker.track()
• VSCode extension — live cost status bar + interactive dashboard

Supported Providers & Models

Provider	Models
Anthropic	claude-opus-4-7, claude-sonnet-4-6, claude-haiku-4-5, claude-3.x
OpenAI	gpt-4o, gpt-4o-mini, gpt-4-turbo, gpt-3.5-turbo, o1, o3-mini
Google	gemini-1.5-pro, gemini-1.5-flash, gemini-2.0-flash
Mistral	mistral-large, mistral-small, codestral
Cohere	command-r-plus, command-r

CLI

# Analyze prompt quality
ai-cost-auditor analyze "Write a function to validate email addresses"

# Show stats
ai-cost-auditor stats --days 7

# Generate report and open in browser
ai-cost-auditor report --days 30 --open

Manual Tracking (any provider)

tracker.track(
    provider="google",
    model="gemini-1.5-flash",
    input_tokens=300,
    output_tokens=120,
    prompt_text="Your prompt here",
)

License

MIT