Repeated request → cache hit

The same request as the first example, sent again. It is answered from the SQLite exact-match cache and marked with x-llmux-cache: hit.

Repeated request → cache hit

examples/cache-hit.json

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

{
  "model": "gpt-4o",
  "messages": [
    { "role": "user", "content": "What is the capital of France?" }
  ]
}

HTTP/1.1 200 OK
x-llmux-cache: hit

{
  "choices": [
    {
      "finish_reason": "stop",
      "index": 0,
      "message": {
        "content": "llmux demo · echo provider.\nRouted to echo/echo-nano (tier 1, task: simple_text). No external call was made — this is a synthetic response so you can see routing and the dashboard end-to-end.\n\nYour message: \"What is the capital of France?\"",
        "role": "assistant"
      }
    }
  ],
  "id": "chatcmpl-echo",
  "model": "echo-nano",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 61,
    "prompt_tokens": 8,
    "total_tokens": 69
  }
}

cache
x-llmux-cache