llmoptimize 3.1.0

Reduce LLM API costs by 90% with ML-powered recommendations and beautiful interactive dashboards

🚀 LLMOptimize - AI Cost Optimization Made Beautiful

Reduce your LLM API costs by 90% with automatic tracking, ML-powered recommendations, and stunning interactive reports.

---

✨ Features

• 🎯 Auto-Tracking - Automatically tracks OpenAI, Anthropic, Groq, and LangChain calls
• 🤖 ML-Powered Recommendations - Smart model suggestions based on your usage patterns
• 📊 Beautiful Interactive Dashboard - Gorgeous terminal UI with animations
• 💰 Real Savings - Users report 85-95% cost reduction
• 🔒 Privacy-First - No prompts sent to server, only metadata
• 📈 Agent Workflow Monitoring - Track multi-step AI agent executions
• 🎨 Zero Configuration - Just import and use!

---

🚀 Quick Start

Installation

pip install llmoptimize

Usage

import llmoptimize
import openai

# Use OpenAI normally - LLMOptimize tracks automatically!
client = openai.OpenAI()
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)

# See your beautiful cost report
llmoptimize.report()

That's it! 🎉

---

📊 Beautiful Interactive Reports

Terminal UI (Default)

llmoptimize.report()  # Interactive animated terminal report

Features:

• 🎬 Animated number counting
• 📈 Real-time cost tracking
• 💡 Personalized recommendations
• 🎨 Beautiful ASCII art
• 🌈 Color-coded insights

Simple Text Output

llmoptimize.report(interactive=False)  # Clean text output

---

🎯 What Gets Tracked

Supported Providers

• ✅ OpenAI - Chat completions, embeddings, images, audio
• ✅ Anthropic - Claude (Opus, Sonnet, Haiku)
• ✅ Groq - Llama, Mixtral, Gemma
• ✅ LangChain - All LLM calls via callback
• ✅ Custom APIs - Manual tracking support

What We Track

{
    "model": "gpt-4",                    # ✅ Model name
    "prompt_tokens": 100,                # ✅ Token count
    "completion_tokens": 50,             # ✅ Token count
    "session_id": "anonymous-uuid"       # ✅ Anonymous ID
}

What we DON'T track:

• ❌ Your actual prompts
• ❌ AI responses
• ❌ Personal information
• ❌ API keys

---

💡 Example Report

╔══════════════════════════════════════════════════════════════╗
║                                                              ║
║     🚀  L L M O P T I M I Z E   R E P O R T  🚀            ║
║                                                              ║
║              Your AI Cost Optimization Summary               ║
║                                                              ║
╚══════════════════════════════════════════════════════════════╝

Analyzing your data... ✓

────────────────────────────────────────────────────────

📊 YOUR USAGE SUMMARY

🚀  Total API Calls Tracked
   15

💰  Total Cost
   $0.1047

💎  Potential Savings
   $0.1038
   That's 99% you could save!

────────────────────────────────────────────────────────

📈 MODEL USAGE

   gpt-4: 10 calls
   gpt-3.5-turbo: 4 calls
   text-embedding-3-large: 1 call

────────────────────────────────────────────────────────

💡 PERSONALIZED RECOMMENDATIONS

╭──────────────────────────────────────────────────────╮
│ #1 Recommendation                                    │
├──────────────────────────────────────────────────────┤
│ 🎯 gpt-4o-mini                                       │
│ 💰 Save 99%                                          │
│                                                      │
│ 💡 Cheaper alternative to gpt-4                      │
╰──────────────────────────────────────────────────────╯

✨ Keep tracking to see more insights!

---

🔧 Advanced Features

Manual Tracking

For custom APIs or non-supported providers:

import llmoptimize

# Track any API call
llmoptimize.track(
    model="custom-model-v1",
    prompt_tokens=100,
    completion_tokens=50,
    provider="custom"
)

LangChain Integration

import llmoptimize
from langchain.llms import OpenAI

# Add callback to track LangChain
llm = OpenAI(callbacks=[llmoptimize.langchain.llmoptimize_callback])

# Use normally - automatically tracked!
result = llm("What is AI?")

---

📈 Real Results

"We reduced our OpenAI bill from $4,200/month to $380/month using LLMOptimize recommendations. The ROI was immediate."

— SaaS Startup, 50K users

"The interactive dashboard makes it so easy to spot optimization opportunities. Saved us 92% on GPT-4 costs."

— AI Research Team

---

🏗️ How It Works

1. Import - import llmoptimize
2. Auto-Patch - Automatically wraps your AI provider SDKs
3. Track - Records metadata (model, tokens) on every call
4. Analyze - ML system analyzes your patterns
5. Recommend - Suggests cheaper alternatives
6. Report - Beautiful visualization of your usage

All happens automatically. Zero code changes required!

---

🔐 Privacy & Security

• ✅ No Prompts Sent - Only metadata (model names, token counts)
• ✅ Anonymous Sessions - Random UUID, no user tracking
• ✅ Open Source Server - Run your own instance if needed
• ✅ No API Key Storage - Your keys stay with you

---

🎨 Installation Options

Basic (Default)

pip install llmoptimize

With All Providers

pip install llmoptimize[full]

Development Tools

pip install llmoptimize[dev]

Everything

pip install llmoptimize[dev,full]

---

📚 Documentation

• Homepage: https://aioptimize.up.railway.app
• Source Code: https://github.com/hackrudra1234/llmoptimize
• Issues: https://github.com/hackrudra1234/llmoptimize/issues

---

🤝 Contributing

This is a proprietary project. For bugs and feature requests, please open an issue.

---

📄 License

Proprietary - All Rights Reserved

---

🎉 Get Started Now!

pip install llmoptimize

import llmoptimize
# Your AI code here...
llmoptimize.report()

Save 90% on AI costs. Beautiful reports. Zero configuration. 🚀

---

Made with ❤️ by the LLMOptimize Team