{
  "id": "chatcmpl-20251010015944503180122WJNB8Eid",
  "model": "gemini-3.6-flash",
  "object": "chat.completion",
  "created": 1760032810,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "你好！很高兴能向你介绍自己。\n\n我是一个大型语言模型（Large Language Model），由 Google 训练和开发。\n\n简单来说，你可以把我理解为一个经过海量文本数据训练、能够理解和生成人类语言的\"智能大脑\"。我的核心能力是处理和生成文本，具体来说，我能做以下这些事情：\n\n**1. 信息查询与知识解答**\n我可以像一部\"会说话的百科全书\"，为你解答各种问题，无论是科学知识、历史事件，还是生活常识。\n\n**2. 创意写作与文本生成**\n我可以根据你的要求，创作各种类型的文本，比如：\n*   **写作**：诗歌、故事、剧本、邮件、演讲稿、广告文案等。\n*   **规划**：为你制定旅行计划、学习大纲、活动方案等。\n*   **头脑风暴**：和你一起碰撞想法，激发新的创意。\n\n**3. 翻译与语言处理**\n我精通多种语言，可以为你提供快速、流畅的翻译服务。同时，我也可以帮你润色、校对、总结或改写文本，让你的表达更清晰、更专业。\n\n**4. 编程与代码辅助**\n我可以编写代码片段、解释代码逻辑、调试错误，或者将代码从一种编程语言\"翻译\"成另一种，是程序员的好帮手。\n\n**5. 逻辑分析与推理**\n我可以帮助你分析复杂的问题，梳理逻辑链条，并根据你提供的信息进行推理和总结。\n\n---\n\n**总而言之**，我的目标是成为一个强大而有用的工具，通过自然语言交流的方式，帮助你更高效地获取信息、完成任务和激发创意。\n\n**需要记住的是：** 我是一个人工智能，我的知识来源于我所学习的数据，并且可能不是最新的。有时我也可能会犯错，所以对于非常重要的信息，建议你进行再次核实。",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ]
      },
      "logprobs": {
        "content": [
          {
            "token": "<string>",
            "logprob": 123,
            "bytes": [
              123
            ],
            "top_logprobs": [
              {
                "token": "<string>",
                "logprob": 123,
                "bytes": [
                  123
                ]
              }
            ]
          }
        ]
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 13,
    "completion_tokens": 1891,
    "total_tokens": 1904,
    "prompt_tokens_details": {
      "cached_tokens": 0,
      "text_tokens": 13,
      "audio_tokens": 0,
      "image_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 1480
    },
    "input_tokens": 0,
    "output_tokens": 0,
    "input_tokens_details": null
  }
}

{
  "error": {
    "code": 400,
    "message": "Invalid request parameters",
    "type": "invalid_request_error"
  }
}

{
  "error": {
    "code": 401,
    "message": "Invalid or expired token",
    "type": "authentication_error"
  }
}

{
  "error": {
    "code": 402,
    "message": "Insufficient quota",
    "type": "insufficient_quota_error",
    "fallback_suggestion": "https://evolink.ai/dashboard/billing"
  }
}

{
  "error": {
    "code": 403,
    "message": "Access denied for this model",
    "type": "permission_error",
    "param": "model"
  }
}

{
  "error": {
    "code": 404,
    "message": "Specified model not found",
    "type": "not_found_error",
    "param": "model",
    "fallback_suggestion": "gemini-3.6-flash"
  }
}

{
  "error": {
    "code": 413,
    "message": "Image file too large",
    "type": "request_too_large_error",
    "param": "content",
    "fallback_suggestion": "compress image to under 10MB"
  }
}

{
  "error": {
    "code": 429,
    "message": "Rate limit exceeded",
    "type": "rate_limit_error",
    "fallback_suggestion": "retry after 60 seconds"
  }
}

{
  "error": {
    "code": 500,
    "message": "Internal server error",
    "type": "internal_server_error",
    "fallback_suggestion": "try again later"
  }
}

{
  "error": {
    "code": 502,
    "message": "Upstream AI service unavailable",
    "type": "upstream_error",
    "fallback_suggestion": "try different model"
  }
}

{
  "error": {
    "code": 503,
    "message": "Service temporarily unavailable",
    "type": "service_unavailable_error",
    "fallback_suggestion": "retry after 30 seconds"
  }
}