Setup Guide

Environment Setup

1. Store Your API Key Securely

Linux/macOS
Windows
.env File

Add to your shell configuration file:

# ~/.bashrc or ~/.zshrc
export MEGALLM_API_KEY="your-api-key-here"

Then reload:

source ~/.bashrc
# or
source ~/.zshrc

Or use a .env file:

echo "MEGALLM_API_KEY=your-api-key-here" >> .env

PowerShell:

[System.Environment]::SetEnvironmentVariable("MEGALLM_API_KEY", "your-api-key-here", "User")

Command Prompt:

setx MEGALLM_API_KEY "your-api-key-here"

Create a .env file in your project root:

MEGALLM_API_KEY=your-api-key-here

Python:

from dotenv import load_dotenv
load_dotenv()

JavaScript:

require('dotenv').config();

Add .env to your .gitignore to avoid committing secrets!

2. Install SDK

Python
JavaScript/TypeScript
Go
Other Languages

# OpenAI SDK (recommended)
pip install openai

# Or Anthropic SDK
pip install anthropic

# For environment variables
pip install python-dotenv

# OpenAI SDK (recommended)
npm install openai

# Or Anthropic SDK
npm install @anthropic-ai/sdk

# For environment variables
npm install dotenv

go get github.com/sashabaranov/go-openai

3. Configure Your Client

Python - OpenAI Format
Python - Anthropic Format
JavaScript - OpenAI Format
JavaScript - Anthropic Format

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://ai.megallm.io/v1",
    api_key=os.getenv("MEGALLM_API_KEY")
)

# Test the connection
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import os
from anthropic import Anthropic

client = Anthropic(
    base_url="https://ai.megallm.io",
    api_key=os.getenv("MEGALLM_API_KEY")
)

# Test the connection
message = client.messages.create(
    model="claude-3.5-sonnet",
    max_tokens=100,
    messages=[{"role": "user", "content": "Hello!"}]
)
print(message.content[0].text)

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://ai.megallm.io/v1',
  apiKey: process.env.MEGALLM_API_KEY
});

// Test the connection
const response = await client.chat.completions.create({
  model: 'gpt-4',
  messages: [{ role: 'user', content: 'Hello!' }]
});
console.log(response.choices[0].message.content);

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  baseURL: 'https://ai.megallm.io',
  apiKey: process.env.MEGALLM_API_KEY
});

// Test the connection
const message = await client.messages.create({
  model: 'claude-3.5-sonnet',
  max_tokens: 100,
  messages: [{ role: 'user', content: 'Hello!' }]
});
console.log(message.content[0].text);

Project Setup

For New Projects

Create project directory:
```
mkdir my-ai-project
cd my-ai-project
```

Initialize project:

# Python
python -m venv venv
source venv/bin/activate
pip install openai python-dotenv

# JavaScript
npm init -y
npm install openai dotenv

Create .env file:

echo "MEGALLM_API_KEY=your-key-here" > .env
echo ".env" >> .gitignore

Create first script: See First Request Guide

For Existing Projects

If you’re already using OpenAI or Anthropic:

Update base URL:

# Before
client = OpenAI(api_key="sk-...")

# After
client = OpenAI(
    base_url="https://ai.megallm.io/v1",
    api_key="your-megallm-key"
)

That’s it! All your existing code works.

IDE Setup

VS Code

Install recommended extensions:

Python extension (for Python)
ESLint (for JavaScript)
REST Client (for testing APIs)

PyCharm / IntelliJ

Configure environment variables in Run Configurations.

AI Coding Assistants

MegaLLM provides a CLI to configure AI coding tools:

npx megallm@latest

This sets up:

Claude Code
Codex/Windsurf
OpenCode

See CLI Documentation for details.

Verify Setup

Test your configuration:

Python
JavaScript
cURL

import os
from openai import OpenAI

# Check API key
api_key = os.getenv("MEGALLM_API_KEY")
if not api_key:
    print("❌ API key not set!")
    exit(1)
print("✅ API key found")

# Test connection
client = OpenAI(
    base_url="https://ai.megallm.io/v1",
    api_key=api_key
)

try:
    response = client.chat.completions.create(
        model="gpt-4",
        messages=[{"role": "user", "content": "Say 'Setup successful!'"}],
        max_tokens=10
    )
    print("✅ Connection successful!")
    print(f"Response: {response.choices[0].message.content}")
except Exception as e:
    print(f"❌ Error: {e}")

import OpenAI from 'openai';

// Check API key
const apiKey = process.env.MEGALLM_API_KEY;
if (!apiKey) {
  console.log('❌ API key not set!');
  process.exit(1);
}
console.log('✅ API key found');

// Test connection
const client = new OpenAI({
  baseURL: 'https://ai.megallm.io/v1',
  apiKey: apiKey
});

try {
  const response = await client.chat.completions.create({
    model: 'gpt-4',
    messages: [{ role: 'user', content: "Say 'Setup successful!'" }],
    max_tokens: 10
  });
  console.log('✅ Connection successful!');
  console.log(`Response: ${response.choices[0].message.content}`);
} catch (error) {
  console.log(`❌ Error: ${error.message}`);
}

curl https://ai.megallm.io/v1/chat/completions \
  -H "Authorization: Bearer $MEGALLM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4",
    "messages": [{"role": "user", "content": "Say setup successful!"}],
    "max_tokens": 10
  }'

Troubleshooting

API key not found

Problem: Environment variable not setSolution:

Check variable name: MEGALLM_API_KEY
Reload shell: source ~/.bashrc
Verify: echo $MEGALLM_API_KEY

Authentication failed (401)

Problem: Invalid API keySolution:

Verify key starts with sk-mega-
Check for extra spaces
Generate new key at dashboard

Connection timeout

Problem: Network or firewall issuesSolution:

Check internet connection
Verify firewall settings
Try without VPN

Module not found

Problem: SDK not installedSolution:

pip install openai  # Python
npm install openai  # JavaScript

Next Steps

First Request

Build your first AI application

Browse Models

Explore 70+ available models

API Reference

Complete API documentation

Best Practices

Tips and common questions

Overview

Getting Started

Environment Setup

1. Store Your API Key Securely

2. Install SDK

3. Configure Your Client

Project Setup

For New Projects

For Existing Projects

IDE Setup

VS Code

PyCharm / IntelliJ

AI Coding Assistants

Verify Setup

Troubleshooting

Next Steps

First Request

Browse Models

API Reference

Best Practices

Overview

Getting Started

Documentation Index

​Environment Setup

​1. Store Your API Key Securely

​2. Install SDK

​3. Configure Your Client

​Project Setup

​For New Projects

​For Existing Projects

​IDE Setup

​VS Code

​PyCharm / IntelliJ

​AI Coding Assistants

​Verify Setup

​Troubleshooting

​Next Steps

First Request

Browse Models

API Reference

Best Practices

Environment Setup

1. Store Your API Key Securely

2. Install SDK

3. Configure Your Client

Project Setup

For New Projects

For Existing Projects

IDE Setup

VS Code

PyCharm / IntelliJ

AI Coding Assistants

Verify Setup

Troubleshooting

Next Steps