GPT-5.2 Codex Code Reasoning API

{
  "messages": [
    {
      "role": "user",
      "content": "Write a Python function that validates email addresses using regex with proper error handling and docstrings"
    }
  ]
}

{
  "model": "openai/gpt-5.2-codex-20260114",
  "usage": {
    "cost": 0.00351225,
    "is_byok": false,
    "cost_details": {
      "upstream_inference_cost": 0.00351225,
      "upstream_inference_prompt_cost": 0.00004025,
      "upstream_inference_completions_cost": 0.003472
    },
    "total_tokens": 271,
    "prompt_tokens": 23,
    "completion_tokens": 248,
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "video_tokens": 0,
      "cached_tokens": 0,
      "cache_write_tokens": 0
    },
    "completion_tokens_details": {
      "audio_tokens": 0,
      "image_tokens": 0,
      "reasoning_tokens": 52
    }
  },
  "content": "```python\nimport re\n\ndef is_valid_email(email: str) -> bool:\n    \"\"\"\n    Validate an email address using a regular expression.\n\n    Parameters\n    ----------\n    email : str\n        The email address to validate.\n\n    Returns\n    -------\n    bool\n        True if the email address is valid, False otherwise.\n\n    Raises\n    ------\n    TypeError\n        If `email` is not a string.\n    ValueError\n        If `email` is an empty string.\n    \"\"\"\n    if not isinstance(email, str):\n        raise TypeError(\"Email must be a string.\")\n    if not email:\n        raise ValueError(\"Email cannot be empty.\")\n\n    # Simple but robust RFC 5322–inspired regex\n    pattern = re.compile(\n        r\"^[A-Za-z0-9._%+-]+@[A-Za-z0-9.-]+\\.[A-Za-z]{2,}$\"\n    )\n    return bool(pattern.match(email))\n```\n\nThis function checks the input type and content, then uses a regex to validate typical email formats."
}