Getting Started with OpenRouter

Create your OpenRouter account, generate your first API key, and make your first API call to an AI model in under 5 minutes.

Step 1: Create Your Account

Getting started with OpenRouter is straightforward:

1. Visit OpenRouter

   Go to openrouter.ai and click Sign Up or Log In.

2. Choose Sign-In Method

   You can sign up with Google, GitHub, or email. GitHub is popular among developers as it connects your coding identity.

3. Complete Registration

   Follow the prompts to finish creating your account. No credit card is required — you can start with free models immediately.

Step 2: Get Your API Key

Once logged in, you need to generate an API key:

1. Navigate to API Keys

   Go to openrouter.ai/keys or click on your profile and select Keys.

2. Create a New Key

   Click Create Key. Give it a descriptive name like "Development" or "Cline". You can optionally set a credit limit.

3. Copy and Save Your Key

   Copy the key immediately — it starts with sk-or-. You will not be able to see it again after leaving the page.

Step 3: Your First API Call

Let's make your first API call using curl. Replace YOUR_API_KEY with the key you just created:

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "meta-llama/llama-4-scout",
    "messages": [
      {
        "role": "user",
        "content": "Hello! What can you help me with?"
      }
    ]
  }'

This example uses meta-llama/llama-4-scout, which is a free model — perfect for testing without spending credits. You should receive a JSON response with the model's reply.

{
  "id": "gen-abc123...",
  "model": "meta-llama/llama-4-scout",
  "choices": [
    {
      "message": {
        "role": "assistant",
        "content": "Hello! I can help you with a wide variety of tasks..."
      }
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 52,
    "total_tokens": 66
  }
}

Understanding Credits and Billing

OpenRouter uses a credit-based system for billing:

• Free models: Several models are available at no cost, including variants of Llama and other open-source models. These are ideal for learning and development.
• Pay-as-you-go: For paid models, you add credits to your account. You are charged per token (input and output) based on each model's pricing.
• No minimums: There are no minimum spending requirements. Add $5 or $500 — you only pay for what you use.
• Credit limits: You can set spending limits on individual API keys to prevent unexpected charges.

Free Models Available

OpenRouter offers several free models that are great for getting started and testing:

Dashboard Overview

The OpenRouter dashboard at openrouter.ai gives you access to:

• Activity: View recent API calls, response times, and token usage in real-time.
• Keys: Manage your API keys, set credit limits, and revoke compromised keys.
• Credits: Check your balance, add funds, and view spending history.
• Models: Browse all available models, compare pricing, and view model details.
• Usage: Detailed analytics showing which models you use most, cost breakdowns, and usage trends.

Usage Tracking

Every API call through OpenRouter is logged with detailed information:

• Which model was used
• Input and output token counts
• Cost of each request
• Response time and latency
• Which API key was used

This makes it easy to audit your AI usage, identify expensive calls, and optimize your spending over time.