{
  "request": {
    "model": "gpt-5.4",
    "messages": [
      { "role": "developer", "content": "You are a concise assistant." },
      { "role": "user", "content": "Explain what an LLM proxy does." }
    ],
    "max_tokens": 256,
    "temperature": null,
    "stream": null
  },
  "response": {
    "id": "chatcmpl-abc123",
    "object": "chat.completion",
    "model": "gpt-5.4",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "An LLM proxy sits between a client and a language model API, translating requests and responses between different API formats."
        },
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 25,
      "completion_tokens": 30,
      "total_tokens": 55
    }
  }
}