Pnyx
Pnyx Docs

Getting Started

Get up and running with Pnyx in under 5 minutes. This guide will walk you through setting up your API key, making your first request, and understanding the core concepts.

Prerequisites

  • A Pnyx account (sign up at pnyx.ai)
  • Basic familiarity with REST APIs
  • Your preferred programming language or cURL

Step 1: Get Your API Key

  1. Log in to your Pnyx dashboard
  2. Navigate to Settings > API Keys
  3. Click Generate New Key
  4. Copy your API key and keep it secure

⚠️ Important: Keep your API key secure and never expose it in client-side code or public repositories.

Step 2: Make Your First Request

Using cURL

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!"}
    ]
  }'

Using Python

import requests

headers = {
    "Authorization": "Bearer YOUR_API_KEY",
    "Content-Type": "application/json"
}

data = {
    "model": "auto",
    "messages": [
        {"role": "user", "content": "Hello, world!"}
    ]
}

response = requests.post(
    "https://api.pnyx.ai/v1/chat/completions",
    headers=headers,
    json=data
)

print(response.json())

Using JavaScript

const response = await fetch('https://api.pnyx.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'auto',
    messages: [
      { role: 'user', content: 'Hello, world!' }
    ]
  })
});

const data = await response.json();
console.log(data);

Step 3: Understanding the Response

A successful request will return a response like this:

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Hello! How can I help you today?"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

Key Concepts

Intelligent Routing

When you use "model": "auto", Pnyx automatically selects the best model for your request based on:

  • Cost efficiency - Balance performance with cost
  • Response speed - Optimize for latency when needed
  • Model capabilities - Route complex tasks to more capable models

Model Selection

You can also specify a particular model:

{
  "model": "gpt-4",
  "messages": [...]
}

Available models include:

  • gpt-4 - OpenAI's most capable model
  • gpt-3.5-turbo - Fast and cost-effective
  • claude-3-opus - Anthropic's most capable model
  • claude-3-sonnet - Balanced performance and speed

Next Steps

Now that you've made your first request, explore these topics:

Need Help?