Authentication

MegaLLM uses API keys for authentication. This guide covers all authentication methods and best practices.

Authentication Methods

Bearer Token

The most common authentication method is using a Bearer token in the Authorization header:

Authorization: Bearer YOUR_API_KEY

API Key Header (Anthropic Format)

For Anthropic-compatible endpoints, you can also use the x-api-key header:

x-api-key: YOUR_API_KEY

Getting Your API Key

Option 1: Device Flow Authentication

The recommended method for obtaining an API key is through device flow:

# Start the authentication process
curl -X POST https://ai.megallm.io/auth/device \
  -H "Content-Type: application/json"

You'll receive a response with:

device_code: Your unique device identifier
user_code: Code to enter for authentication
verification_uri: URL to visit for authentication

Option 2: Dashboard

You can generate an API key from the MegaLLM dashboard:

Visit the MegaLLM dashboard
Navigate to API Keys section
Generate a new API key
Copy the key and store it securely

Option 3: CLI Tool

If you have the MegaLLM CLI installed:

megallm auth token

Security Best Practices

Never expose your tokens: Always store tokens in environment variables or secure vaults, never in code.

Environment Variables

# Add to ~/.bashrc or ~/.zshrc
export MEGALLM_API_KEY="your_api_key_here"

# Or use a .env file
echo "MEGALLM_API_KEY=your_api_key_here" >> .env

# Set environment variable
[System.Environment]::SetEnvironmentVariable("MEGALLM_API_KEY", "your_api_key_here", "User")

# Or use command prompt
setx MEGALLM_API_KEY "your_api_key_here"

# In Dockerfile
ENV MEGALLM_API_KEY=${MEGALLM_API_KEY}

# Or in docker-compose.yml
environment:
  - MEGALLM_API_KEY=${MEGALLM_API_KEY}

Using SDKs

OpenAI SDK

from openai import OpenAI

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

response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}]
)

Anthropic SDK

from anthropic import Anthropic

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

message = client.messages.create(
    model="claude-3.5-sonnet",
    max_tokens=100,
    messages=[{"role": "user", "content": "Hello!"}]
)

LangChain Integration

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://ai.megallm.io/v1",
    api_key=os.getenv("MEGALLM_API_KEY"),
    model="gpt-4"
)

response = llm.invoke("Hello!")

Troubleshooting

Common Authentication Errors

Error Code	Message	Solution
401	Unauthorized	Check if your API key is valid and not expired
403	Forbidden	Verify API key has required access
429	Rate Limited	Wait and retry or contact support

Debugging Authentication

Enable debug mode to see detailed authentication information:

curl https://ai.megallm.io/v1/chat/completions \
  -H "Authorization: Bearer $MEGALLM_API_KEY" \
  -H "X-Debug-Auth: true" \
  -d '{"model": "gpt-4", "messages": [...]}'

Need Help? Check our FAQ or contact support if you're experiencing authentication issues.

Authentication

On this page