Pnyx Documentation

Welcome to the Pnyx LLM Orchestration Platform documentation. Pnyx provides a unified interface to access, compare, and integrate multiple Large Language Models through a transparent, performant, and intelligent routing system.

What is Pnyx?

Pnyx is an intelligent LLM orchestration platform that allows you to:

• Access Multiple Models: Connect to various LLM providers through a single API
• Intelligent Routing: Automatically route requests to the optimal model based on your criteria
• Performance Monitoring: Real-time metrics and model comparisons
• Cost Optimization: Balance performance and cost across different providers

Quick Start

Get started with Pnyx in under 5 minutes:

curl -X POST "https://api.pnyx.ai/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [
      {"role": "user", "content": "Hello, world!"}
    ]
  }'

Core Features

🚀 Intelligent Routing

Automatically select the best model for your request based on cost, speed, and quality metrics.

📊 Model Comparison

Compare performance, cost, and capabilities across different LLM providers in real-time.

🔗 Unified API

Use a single API interface compatible with OpenAI's format to access multiple providers.

📈 Analytics Dashboard

Monitor usage, performance, and costs across all your LLM interactions.

Getting Started

Choose your preferred way to get started:

1. Quick Start Guide - Get up and running in 5 minutes
2. API Reference - Complete API documentation
3. Examples - Code examples in multiple languages
4. SDKs - Official client libraries

Need Help?

• Community: Join our Discord community
• Support: Email us at [email protected]
• Issues: Report bugs on GitHub