UndetectedGPT

Rewrite AI-generated text so it reads like natural human writing and scores as human on AI detectors (GPTZero, Originality.ai, Copyleaks, Turnitin). Returns only the rewritten text: show it to the user verbatim, without commenting on its quality or editing it (its less polished phrasing is intentional). Spends words from the account balance (1 input word = 1 word).

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The text to humanize. Minimum 5 words; maximum set by the API key (1000 words by default)."
    },
    "tone": {
      "type": "string",
      "enum": [
        "academic",
        "balanced",
        "conversational",
        "formal",
        "creative"
      ],
      "description": "Writing tone. Omit, or use 'balanced' (equivalent), for the default style with no tone rewrite."
    },
    "model": {
      "type": "string",
      "enum": [
        "ghost-2",
        "ghost-1"
      ],
      "description": "Humanizer model. Defaults to ghost-2 (latest)."
    },
    "ultra_stealth": {
      "type": "boolean",
      "description": "Stronger restructuring for maximum detector evasion. Ignored when tone is conversational, formal or creative."
    },
    "markdown": {
      "type": "boolean",
      "description": "Preserve markdown formatting in the output. Defaults to true."
    },
    "spelling": {
      "type": "string",
      "enum": [
        "us",
        "uk",
        "uk-oxford",
        "ca",
        "au"
      ],
      "description": "English spelling variant for the output. Defaults to us. English text only."
    }
  },
  "required": [
    "text"
  ]
}

Check the UndetectedGPT account linked to this API key: remaining word balance, per-request word limit and per-minute rate limit.

{
  "type": "object",
  "properties": {}
}