GPT-5.3 Codex (via x402 Gateway)

{
  "model": "gpt-5.3-codex",
  "messages": [
    {
      "role": "user",
      "content": "Write a Python function that validates email addresses using regex, includes proper error handling, and returns a boolean indicating validity. Include type hints and a docstring."
    }
  ],
  "max_tokens": 500
}

{
  "model": "openai/gpt-5.3-codex-20260224",
  "usage": {
    "cost": 0.00605675,
    "is_byok": false,
    "cost_details": {
      "upstream_inference_cost": 0.00605675,
      "upstream_inference_prompt_cost": 0.00006475,
      "upstream_inference_completions_cost": 0.005992
    },
    "total_tokens": 465,
    "prompt_tokens": 37,
    "completion_tokens": 428,
    "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": 64
    }
  },
  "content": "```python\nimport re\nfrom typing import Pattern\n\n# A practical (not fully RFC 5322-complete) email regex.\n_EMAIL_REGEX: Pattern[str] = re.compile(\n    r\"^(?=.{1,254}$)(?=.{1,64}@)\"\n    r\"[A-Za-z0-9.!#$%&'*+/=?^_`{|}~-]+\"\n    r\"@\"\n    r\"(?:[A-Za-z0-9-]+\\.)+[A-Za-z]{2,63}$\"\n)\n\n\ndef is_valid_email(email: str) -> bool:\n    \"\"\"\n    Validate whether a string is a syntactically valid email address.\n\n    This function performs a regex-based validation with basic constraints:\n    - Total length <= 254 characters\n    - Local part (before '@') <= 64 characters\n    - Domain contains at least one dot and valid label characters\n    - Top-level domain length between 2 and 63 letters\n\n    Args:\n        email: The email address string to validate.\n\n    Returns:\n        True if the email appears valid by the regex rules, otherwise False.\n\n    Error Handling:\n        - Returns False if `email` is not a string.\n        - Returns False if regex matching fails unexpectedly.\n    \"\"\"\n    if not isinstance(email, str):\n        return False\n\n    candidate = email.strip()\n    if not candidate:\n        return False\n\n    try:\n        return _EMAIL_REGEX.fullmatch(candidate) is not None\n    except re.error:\n        # Defensive fallback in case of regex engine issues\n        return False\n```\n\nIf you want, I can also provide a stricter version (e.g., disallowing consecutive dots in the local part) or one that supports internationalized domains."
}