Introduction

Welcome to COZHUB! This guide will walk you through everything you need to start using our unified AI API. By the end, you'll have made your first API request to any of our 60+ AI models.

What you'll learn:

• Creating your COZHUB account
• Generating API keys
• Making your first API request
• Switching between AI models
• Best practices for production

Prerequisites

Before you begin, make sure you have:

• A valid email address
• Basic familiarity with REST APIs
• Node.js 18+ or Python 3.8+ (for the code examples)

Step 1: Create Your Account

Visit cozhub.ai/auth/signup

Enter your email and create a password

Verify your email address

Bonus: New accounts receive $5 in free credits!

Step 2: Generate an API Key

After logging in:

Navigate to Dashboard → API Keys

Click Create New Key

Give your key a descriptive name (e.g., "Development Key")

Copy and save your key securely — you won't be able to see it again!

Your API key looks like this:
sk-coz-xxxxxxxxxxxxxxxxxxxxxxxxxxxx

⚠️ Security Tip: Never commit API keys to version control. Use environment variables instead.

Step 3: Install the SDK

Choose your preferred language:

JavaScript/TypeScript

npm install openai
COZHUB is compatible with the OpenAI SDK

Python

pip install openai

cURL

No installation needed — cURL comes pre-installed on most systems.

Step 4: Make Your First Request

JavaScript/TypeScript

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.cozhub.ai/v1',
  apiKey: process.env.COZHUB_API_KEY,
});

async function main() {
  const response = await client.chat.completions.create({
    model: 'gpt-4o',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'What is the capital of France?' }
    ],
  });

  console.log(response.choices[0].message.content);
}

main();

Python

from openai import OpenAI
import os

client = OpenAI(
    base_url="https://api.cozhub.ai/v1",
    api_key=os.environ.get("COZHUB_API_KEY"),
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of France?"}
    ]
)

print(response.choices[0].message.content)

cURL

curl https://api.cozhub.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COZHUB_API_KEY" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is the capital of France?"}
    ]
  }'

Expected Response:

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 8,
    "total_tokens": 33
  }
}

Step 5: Try Different Models

The magic of COZHUB is switching models with a single line change:

// Use Claude instead of GPT-4
const response = await client.chat.completions.create({
  model: 'claude-3-5-sonnet',  // Just change the model name!
  messages: [...]
});

// Or try DeepSeek for cost savings
const response = await client.chat.completions.create({
  model: 'deepseek-v3',
  messages: [...]
});

// Or Gemini for multi-modal tasks
const response = await client.chat.completions.create({
  model: 'gemini-2.0-flash',
  messages: [...]
});

Available Models

Here are some popular models to try:

Model

Best For

Price (per 1M tokens)

gpt-4o	General tasks, reasoning	$2.50 / $10.00
claude-3-5-sonnet	Long context, analysis	$3.00 / $15.00
gemini-2.0-flash	Fast responses	$0.075 / $0.30
deepseek-v3	Cost-effective	$0.27 / $1.10

See the full list in our Models Catalog.

Best Practices

1. Use Environment Variables

# .env file
COZHUB_API_KEY=sk-coz-xxxxxxxxxxxx

2. Handle Errors Gracefully

try {
  const response = await client.chat.completions.create({...});
} catch (error) {
  if (error.status === 429) {
    // Rate limited - wait and retry
  } else if (error.status === 402) {
    // Insufficient credits
  }
}

3. Set Reasonable Timeouts

const client = new OpenAI({
  baseURL: 'https://api.cozhub.ai/v1',
  apiKey: process.env.COZHUB_API_KEY,
  timeout: 30000,  // 30 seconds
});

4. Monitor Your Usage

Check your dashboard regularly to:

• Track spending
• Identify expensive queries
• Set up usage alerts

Next Steps

Now that you're up and running:

Explore the Models: Try different models to find what works best

Read the API Docs: Check our API Reference

Build Something: Start with a simple chatbot or content generator

Join the Community: Ask questions on our Discord

Need Help?

• 📚 Documentation
• 💬 Discord Community
• 📧 Email Support

Happy building! 🚀