Mintii Router: Intelligent LLM Model Selection and Optimization Library. Automatically selects the best Large Language Model for each prompt, optimizing for cost, quality, and performance.
Project description
Mintii Router
The intelligent LLM model selection and optimization library by Mintii Labs.
About Mintii Router
Mintii Router is a sophisticated AI model selection system that automatically chooses the best Large Language Model (LLM) for each specific prompt, optimizing for both cost and quality. Our system evaluates over 20 different LLMs in real-time to ensure you get the best possible response while minimizing costs.
Key Features
- 🎯 Intelligent Model Selection: Automatically selects the most suitable LLM for each prompt
- 💰 Cost Optimization: Achieve up to 80% cost reduction through smart model routing
- 🚀 Quality Assurance: Maintains high-quality responses through sophisticated model evaluation
- 🔄 Adaptive Learning: Continuously improves selection criteria based on performance data
- 📊 Usage Analytics: Track and optimize your LLM usage patterns
Installation
pip install mintii-router
Quick Start
from mintii import Router
from dotenv import load_dotenv
import os
# Load your API keys
load_dotenv()
# Initialize the router
router = Router(api_key=os.getenv('MINTII_API_KEY'))
# Get a response
response = router.generate("Explain quantum computing in simple terms")
print(response.content)
Features
-
Smart Model Selection: Automatically chooses the best model based on:
- Prompt complexity
- Required capabilities
- Cost constraints
- Performance requirements
-
Cost Optimization: Reduces costs by:
- Selecting cost-effective models
- Optimizing token usage
- Balancing quality and cost
-
Quality Assurance: Maintains high standards through:
- Model capability matching
- Response quality monitoring
- Consistent performance tracking
Documentation
For full documentation, visit docs.mintii.ai
Support
- Email: support@mintiilabs.com
- Documentation: docs.mintii.ai
- Issues: GitHub Issues
License
Proprietary. Copyright © 2024 Mintii Labs. All rights reserved.
Project details
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 mintii-0.0.1.tar.gz.
File metadata
- Download URL: mintii-0.0.1.tar.gz
- Upload date:
- Size: 4.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d66a03704ef44edccb94f9e8980d1ec4e0a4751ec8c866643e23a5aecbe2349c
|
|
| MD5 |
a0b4f570856c5281f848b4321e6388ad
|
|
| BLAKE2b-256 |
cbe8c4f12ac6fe1560daae5d52e82bb6c7b04b14009046c0883cd7f2c059c2bf
|
File details
Details for the file mintii-0.0.1-py3-none-any.whl.
File metadata
- Download URL: mintii-0.0.1-py3-none-any.whl
- Upload date:
- Size: 4.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.12.4
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
806d656b771c4eb0e8ed4a3f8586bae815dc12360430138a08ba088bf34eaaf6
|
|
| MD5 |
aa8a7397b61c6454347230f6aed117e0
|
|
| BLAKE2b-256 |
cca633bfc8503488c66dd45114bf131fd99dc12958ab96e2431d59359a573276
|