Architecture question → tier 4

"Architecture" and "trade-offs" put the prompt into the architecture class. It needs tier 4, so it never lands on a small model.

Architecture question → tier 4

examples/architecture.json

POST /v1/chat/completions
content-type: application/json

{
  "model": "gpt-4o",
  "messages": [
    { "role": "user", "content": "Explain the architecture trade-offs between a monolith and microservices." }
  ]
}

HTTP/1.1 200 OK
x-llmux-echo: 1

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "llmux demo · echo provider.\nRouted to echo/echo-pro (tier 4, task: architecture). No external call was made — this is a synthetic response so you can see routing and the dashboard end-to-end.\n\nYour message: \"Explain the architecture trade-offs between a monolith and microservices.\"",
        "role": "assistant"
      }
    }
  ],
  "id": "chatcmpl-echo",
  "model": "echo-pro",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 72,
    "prompt_tokens": 19,
    "total_tokens": 91
  }
}

architecture
tier 4