Detect AI-generated text

Detect AI-generated text: overall verdict with confidence, AI/human/AI-assisted fractions, and a segment-by-segment breakdown with per-segment humanizer flags. Price scales with length: $0.06 per 100 words, rounded up; minimum $0.06

Paid test badge: not yet. The checks above are free: we call the tool without paying and read the payment request it sends back. The Verified badge needs paid calls whose answers match the promised output, and nobody can buy a badge.

Endpoint

POST https://glim.sh/api/v1/detect/ai

Our checks, last 30 days

Example input (from the provider)

{
  "body": {
    "text": "Detection quality depends on length, so pass at least a paragraph of the text you want scored rather than a single sentence."
  },
  "bodyType": "json",
  "method": "POST",
  "type": "http"
}

Promised output schema (from the provider)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "input": {
      "additionalProperties": false,
      "properties": {
        "body": {
          "description": "Input for POST /api/v1/detect/ai",
          "properties": {
            "text": {
              "description": "Text to analyze, plain text, 50+ characters, max 20,000. Detection reliability improves with length; very short texts return lower-confidence verdicts.",
              "minLength": 50,
              "type": "string"
            }
          },
          "required": [
            "text"
          ],
          "type": "object"
        },
        "bodyType": {
          "enum": [
            "json",
            "form-data",
            "text"
          ],
          "type": "string"
        },
        "method": {
          "enum": [
            "POST"
          ],
          "type": "string"
        },
        "type": {
          "const": "http",
          "type": "string"
        }
      },
      "required": [
        "type",
        "method",
        "bodyType",
        "body"
      ],
      "type": "object"
    },
    "output": {
      "properties": {
        "example": {
          "properties": {
            "confidence": {
              "description": "Confidence carrying the overall verdict: High, Medium, or Low",
              "type": "string"
            },
            "cost_usd": {
              "description": "Amount charged for this call, in USD",
              "type": "number"
            },
            "fraction_ai": {
              "description": "Fraction of the text judged AI-generated, 0-1",
              "type": "number"
            },
            "fraction_ai_assisted": {
              "description": "Fraction judged AI-assisted, 0-1",
              "type": "number"
            },
            "fraction_human": {
              "description": "Fraction judged human-written, 0-1",
              "type": "number"
            },
            "headline": {
              "description": "Short verdict, e.g. 'AI Generated', 'AI Detected', 'Human Written'",
              "type": "string"
            },
            "num_ai_assisted_segments": {
              "description": "Segments labeled AI-Assisted",
              "maximum": 9007199254740991,
              "minimum": -9007199254740991,
              "type": "integer"
            },
            "num_ai_segments": {
              "description": "Segments labeled AI-Generated",
              "maximum": 9007199254740991,
              "minimum": -9007199254740991,
              "type": "integer"
            },
            "num_human_segments": {
              "description": "Segments labeled Human",
              "maximum": 9007199254740991,
              "minimum": -9007199254740991,
              "type": "integer"
            },
            "prediction": {
              "description": "One-sentence verdict in plain English",
              "type": "string"
            },
            "prediction_short": {
              "description": "Verdict class: AI, Mixed, or Human",
              "type": "string"
            },
            "segments": {
              "description": "Per-segment breakdown, in reading order",
              "items": {
                "properties": {
                  "ai_assistance_score": {
                    "description": "Same value as score, under the upstream detector's field name",
                    "type": "number"
                  },
                  "confidence": {
                    "description": "Detector confidence for this segment: High, Medium, or Low",
                    "type": "string"
                  },
                  "end_index": {
                    "description": "Character offset just past this segment's last word in the text you submitted (exclusive)",
                    "maximum": 9007199254740991,
                    "minimum": -9007199254740991,
                    "type": "integer"
                  },
                  "humanizer_score": {
                    "description": "Humanizer likelihood, 0-1.",
                    "type": "number"
                  },
                  "is_humanized": {
                    "description": "True when this segment reads as AI output passed through a paraphrasing/'humanizer' tool. Absent means not evaluated, not false.",
                    "type": "boolean"
                  },
                  "label": {
                    "description": "Detector verdict for this segment (e.g. 'AI-Generated', 'Human')",
                    "type": "string"
                  },
                  "preview": {
                    "description": "Opening excerpt of the segment",
                    "type": "string"
                  },
                  "score": {
                    "description": "AI-assistance score for this segment, 0-1",
                    "type": "number"
                  },
                  "start_index": {
                    "description": "Character offset of this segment's first word in the text you submitted",
                    "maximum": 9007199254740991,
                    "minimum": -9007199254740991,
                    "type": "integer"
                  },
                  "text": {
                    "description": "Full text of this segment, sliced from the text you submitted",
                    "type": "string"
                  },
                  "token_length": {
                    "description": "Tokens in this segment, as counted by the detector",
                    "maximum": 9007199254740991,
                    "minimum": -9007199254740991,
                    "type": "integer"
                  },
                  "word_count": {
                    "maximum": 9007199254740991,
                    "minimum": -9007199254740991,
                    "type": "integer"
                  },
                  "word_end": {
                    "description": "1-based word position where this seg

This page as JSON