#Quickstart

GetRouter gives you one API key for multiple model providers and API protocols. This quickstart sends a first OpenAI-compatible Chat Completions request; you can choose another protocol after the basic setup works.

#1. Create an API key

Sign in to GetRouter, open the API Keys page, and create a key.

Store the key securely. Examples in this documentation use YOUR_API_KEY and never require you to paste a real credential into the docs.

#2. Choose a model

Open the live Models page and copy the exact model ID you want to call. Model availability and pricing can change, so the live catalog is the source of truth.

#3. Send your first request

Replace YOUR_API_KEY and MODEL_ID, then run:

curl https://getrouter.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "MODEL_ID",
    "messages": [
      {"role": "user", "content": "Explain what an API router does in one sentence."}
    ]
  }'

The generated text is returned in choices[0].message.content.

#Choose the API for your application

Protocols do not all use the same endpoint shape. Review Base URL and Endpoints before changing SDKs or protocols.

#Connect an AI tool instead

If you are configuring a coding agent or desktop client rather than writing code, start with Integrations and check the compatibility guide. Each tool page lists the URL and protocol it expects.

#Next steps

• Create and manage API keys
• Choose a model
• Migrate from OpenAI
• Troubleshoot a connection