{
  "id": "chatcmpl-20251010015944503180122WJNB8Eid",
  "model": "gemini-2.5-flash",
  "object": "chat.completion",
  "created": 1760032810,
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm pleased to introduce myself.\n\nI'm a Large Language Model, trained and developed by Google.\n\nSimply put, you can think of me as a \"smart brain\" that has been trained on massive amounts of text data and is able to understand and generate human language. My core capability is processing and generating text. Specifically, I can do the following:\n\n**1. Information Query & Knowledge Answering**\nI can act like a \"talking encyclopedia,\" answering various questions, whether they're about scientific knowledge, historical events, or everyday facts.\n\n**2. Creative Writing & Text Generation**\nI can create various types of text based on your requirements, such as:\n*   **Writing**: Poetry, stories, scripts, emails, speeches, advertising copy, etc.\n*   **Planning**: Travel plans, study outlines, event proposals, etc.\n*   **Brainstorming**: Working with you to generate new ideas and spark creativity.\n\n**3. Translation & Language Processing**\nI'm proficient in multiple languages and can provide fast, fluent translation services. I can also help you polish, proofread, summarize, or rewrite text to make your expression clearer and more professional.\n\n**4. Programming & Code Assistance**\nI can write code snippets, explain code logic, debug errors, or \"translate\" code from one programming language to another, making me a helpful companion for programmers.\n\n**5. Logical Analysis & Reasoning**\nI can help you analyze complex problems, organize logical chains, and make inferences and summaries based on the information you provide.\n\n---\n\n**In summary**, my goal is to be a powerful and useful tool that helps you obtain information more efficiently, complete tasks, and spark creativity through natural language communication.\n\n**Remember:** I'm an artificial intelligence, my knowledge comes from the data I've learned, and it may not be the most up-to-date. Sometimes I may also make mistakes, so for very important information, I recommend you verify it again.",
        "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": "無効なリクエストパラメータ",
    "type": "invalid_request_error"
  }
}

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

{
  "error": {
    "code": 402,
    "message": "クォータ不足",
    "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-2.5-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": "レート制限を超過しました",
    "type": "rate_limit_error",
    "fallback_suggestion": "retry after 60 seconds"
  }
}

{
  "error": {
    "code": 500,
    "message": "内部サーバーエラー",
    "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": "サービス一時利用不可",
    "type": "service_unavailable_error",
    "fallback_suggestion": "retry after 30 seconds"
  }
}