{
  "request": {
    "method": "POST",
    "url": "https://api.wanapis.com/v1/chat/completions",
    "headers": {
      "Authorization": "Bearer sk-wanapis-REDACTED",
      "Content-Type": "application/json"
    },
    "body": {
      "model": "claude-opus-4-7",
      "messages": [
        { "role": "system", "content": "You are a concise API documentation assistant." },
        { "role": "user", "content": "Explain RAG in three sentences." }
      ],
      "temperature": 0.3,
      "max_tokens": 256
    }
  },
  "response": {
    "id": "chatcmpl-wanapis-9f2c1c",
    "object": "chat.completion",
    "created": 1748381400,
    "model": "claude-opus-4-7",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "Retrieval-Augmented Generation (RAG) pairs a large language model with an external knowledge store, retrieving relevant passages at query time. Those passages are concatenated into the prompt so the model grounds its answer in fresh, source-of-truth data rather than only its training corpus. The result is a system that can cite, update, and constrain its outputs without retraining the underlying model."
        },
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 42,
      "completion_tokens": 88,
      "total_tokens": 130
    }
  }
}