{
  "request": {
    "method": "POST",
    "url": "https://api.hyperbolic.xyz/v1/chat/completions",
    "headers": {
      "Authorization": "Bearer YOUR_HYPERBOLIC_API_KEY",
      "Content-Type": "application/json"
    },
    "body": {
      "model": "deepseek-ai/DeepSeek-V3",
      "messages": [
        { "role": "system", "content": "You are an API Evangelist research assistant." },
        { "role": "user", "content": "Explain prompt caching in two sentences." }
      ],
      "max_tokens": 256,
      "temperature": 0.7,
      "stream": false
    }
  },
  "response": {
    "id": "chatcmpl-abc123",
    "object": "chat.completion",
    "created": 1748160000,
    "model": "deepseek-ai/DeepSeek-V3",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "Prompt caching stores reusable portions of a prompt server-side so identical prefixes do not have to be re-encoded on every request. This lowers latency and cost when an application repeatedly sends the same long system prompts, tools, or RAG context."
        },
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 28,
      "completion_tokens": 51,
      "total_tokens": 79
    }
  }
}