GET STARTED

Your first call, in three steps

If you already use an OpenAI-compatible client, the only thing that changes is the base URL.

  1. 1

    Create an API key

    Keys start with sk-rb-. The plaintext is shown once, at creation — we store only a hash, so nobody (including us) can read it back. Copy it then.

    Create an account
  2. 2

    Point your client at this base URL

    Any OpenAI SDK works as-is. Set the base URL and pass your key as the bearer token.

    Base URL
    https://routerbase.seeksvc.com/v1
  3. 3

    Send the first request

    Use any model id from the catalog. Cost is estimated and held before the call, then settled against actual usage.

    curl
    curl https://routerbase.seeksvc.com/v1/chat/completions \
      -H "Authorization: Bearer $ROUTERBASE_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "openai/gpt-5.4-mini",
        "messages": [{"role": "user", "content": "Hello"}]
      }'
    Python
    from openai import OpenAI
    
    client = OpenAI(
        base_url="https://routerbase.seeksvc.com/v1",
        api_key="sk-rb-...",  # create one at /dashboard/keys
    )
    
    resp = client.chat.completions.create(
        model="openai/gpt-5.4-mini",
        messages=[{"role": "user", "content": "Hello"}],
    )
    print(resp.choices[0].message.content)
    Node
    import OpenAI from "openai"
    
    const client = new OpenAI({
      baseURL: "https://routerbase.seeksvc.com/v1",
      apiKey: process.env.ROUTERBASE_API_KEY,
    })
    
    const resp = await client.chat.completions.create({
      model: "openai/gpt-5.4-mini",
      messages: [{ role: "user", content: "Hello" }],
    })
    console.log(resp.choices[0].message.content)

What to look at next