Quickstart

Use RouterBase as an OpenAI-compatible gateway

RouterBase exposes an OpenAI-compatible API at https://routerbase.com/v1. For many chat-completions integrations, the first experiment is a base URL, API key, and model id change.

Minimal request

curl https://routerbase.com/v1/chat/completions \
  -H "Authorization: Bearer $ROUTERBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-2.5-flash",
    "messages": [
      { "role": "user", "content": "Explain RouterBase in one sentence." }
    ]
  }'

Node.js pattern

const response = await fetch("https://routerbase.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ROUTERBASE_API_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    model: process.env.ROUTERBASE_MODEL || "google/gemini-2.5-flash",
    messages: [
      { role: "user", content: "Draft a short product update." }
    ]
  })
});

Rollout notes

• Keep the model id configurable.
• Test one workflow before changing production traffic.
• Track latency, cost, error rate, and output quality.
• Use the API collections for a request smoke test before writing code.

Next: Import RouterBase into Postman, Bruno, or Insomnia.