Reduce LLM API costs by 90% with automatic tracking and AI-powered recommendations
Project description
AIOptimize - Reduce LLM API Costs by 90%
Drop-in SDK that automatically tracks costs, recommends cheaper models, and optimizes AI workflows.
๐ Quick Start
pip install llmoptimize
import llmoptimize
# Your code works exactly the same
import openai
client = openai.OpenAI()
response = client.chat.completions.create(
model="gpt-4",
messages=[{"role": "user", "content": "Hello!"}]
)
# See your costs and savings
llmoptimize.report()
Output:
๐ฐ COST REPORT
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Total Calls: 47
Total Cost: $2.34
Potential Savings: $2.11 (90%)
๐ก RECOMMENDATIONS
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โ Use gpt-3.5-turbo instead of gpt-4 for simple tasks
โ Estimated savings: $1.85/day
โจ Features
๐ฏ Magic Mode (Default)
Zero code changes - just import llmoptimize and it works.
๐ค AI-Powered Recommendations
Smart analysis of each API call with confidence scores and reasoning.
๐ Comprehensive Tracking
- Real-time cost tracking
- Token usage analytics
- Model performance insights
- Automatic report generation
๐ Code Auditing
Analyze Python code BEFORE running to find optimization opportunities.
๐ญ Agent Optimization
Track multi-step AI agent workflows with loop detection and context optimization.
๐ Free Trial
100 calls with full access to all features - no credit card required.
After 100 calls, choose your plan:
- Starter: $29/month - 10,000 calls
- Pro: $99/month - Unlimited calls + dashboard
- Enterprise: Custom pricing
๐ฆ Supported Providers
โ OpenAI (GPT-4, GPT-4o, o1, o3, embeddings) โ Anthropic (Claude 3, Claude 3.5) โ Google (Gemini 1.5, 2.0) โ Groq (Llama, Mixtral, Gemma) โ Mistral (Large, Small, Nemo) โ Cohere (Command R+)
72+ models tracked automatically.
๐ Privacy & Security
โ No prompt content sent - Only categories โ API keys stay local - Never sent to our servers โ Anonymized data only - Random session IDs โ GDPR compliant - Full data export available
๐ License
Proprietary - See LICENSE file.
Free 100-call trial included. Paid license required for continued use.
๐ค Support
- ๐ง Email: hakrudra@gmail.com
- ๐ Docs: Full documentation
- ๐ Issues: GitHub Issues
Made with โค๏ธ by llmOptimize Team
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file llmoptimize-1.0.2.tar.gz.
File metadata
- Download URL: llmoptimize-1.0.2.tar.gz
- Upload date:
- Size: 96.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
80a2345917c39396f1404bb024bfe2f7dac234dc06dcd04d7def96893c69faf0
|
|
| MD5 |
137c2b0b4b239781589b6ace82515885
|
|
| BLAKE2b-256 |
d8d54b78e1f6daa697f654e834c9b120154dabfedf7b5dce81fdc64f82512ad9
|
File details
Details for the file llmoptimize-1.0.2-py3-none-any.whl.
File metadata
- Download URL: llmoptimize-1.0.2-py3-none-any.whl
- Upload date:
- Size: 108.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e80ca96a7c831153550eebfbcfe31b167f772700da27e628cf26fec282c48067
|
|
| MD5 |
8c35358533b10a3f5ca05b1e567f521c
|
|
| BLAKE2b-256 |
35eb3b6cefd5ed4184c526b02ea552a65ecde94d5845cc0e414b016ef6feeee7
|