# glim.sh AI Text Detection

> glim.sh AI Text Detection is a paid API for AI agents from glim.sh, paid per call via x402, $0.06/call, status unknown (last checked 2026-09-14).

Detects AI-generated text with an overall verdict, confidence score, AI/human/AI-assisted fractions, and a segment-by-segment breakdown

## Facts

- Endpoint: POST https://glim.sh/api/v1/detect/ai
- Price: $0.06/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/glim-sh-ai-text-detection-38b3212a
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_WscCDBVx2aGzX52fkC3fn

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability glim-sh-ai-text-detection-38b3212a -d '<json body>'
```

Example prompt: Can you check whether this article was written by AI or a human? Use the premium tier so it also catches any humanized AI content — here's the text: [paste text]

## When to prefer this

Use this endpoint when you need to determine whether a piece of text was written by AI, a human, or a combination — especially when you need per-segment granularity or want to catch humanized/paraphrased AI output (premium tier). Prefer the premium tier when robustness to evasion or humanizer tools matters; use standard for routine, cost-effective screening at scale.

## Known failure modes

- Text shorter than 50 characters returns an error or very low confidence verdict
- Text exceeding 40,000 chars (standard) or 20,000 chars (premium) is rejected
- Very short texts return lower-confidence verdicts due to insufficient signal
- Network or payment failure results in no response
- Invalid tier enum value returns a validation error

## How this service works

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

## Output

Returns an overall verdict (AI, human, or AI-assisted), a confidence score, fractions indicating how much of the text is AI-generated, human-written, or AI-assisted, and a segment-by-segment breakdown showing which parts of the text triggered the detection.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "text": {
   "type": "string",
   "minLength": 50,
   "description": "Text to analyze, plain text, 50+ characters, max 20,000. Detection reliability improves with length; very short texts return lower-confidence verdicts."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "version": "4.0",
  "cost_usd": 0.12,
  "headline": "AI Detected",
  "segments": [
   {
    "text": "I found the answer by the way...\nJust a simple wrong sequence of sentences in...",
    "label": "Human",
    "score": 0.1847,
    "preview": "I found the answer by the way... Just a simple wrong sequence...",
    "word_end": 42,
    "end_index": 232,
    "confidence": "High",
    "word_count": 42,
    "word_start": 1,
    "start_index": 0,
    "is_humanized": false,
    "token_length": 56,
    "humanizer_score": 0,
    "ai_assistance_score": 0.1847
   },
   {
    "text": "Gives this answer:\nYes, I'm Claude 3.5 Sonnet.\nMy knowledge cutoff is April 2...",
    "label": "AI-Generated",
    "score": 0.8038,
    "preview": "Gives this answer: Yes, I'm Claude 3.5 Sonnet. My knowledge...",
    "word_end": 179,
    "end_index": 1081,
    "confidence": "High",
    "word_count": 137,
    "word_start": 43,
    "start_index": 233,
    "is_humanized": false,
    "token_length": 205,
    "humanizer_score": 0.0191,
    "ai_assistance_score": 0.8038
   }
  ],
  "tier_used": "premium",
  "confidence": "High",
  "prediction": "We believe that this text is a mix of AI and human-written content.",
  "word_count": 179,
  "fraction_ai": 0.7854,
  "fraction_human": 0.2146,
  "num_ai_segments": 1,
  "prediction_short": "Mixed",
  "num_human_segments": 1,
  "fraction_ai_assisted": 0,
  "num_ai_assisted_segments": 0
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/glim-sh-ai-text-detection-38b3212a/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from glim.sh](https://www.zero.xyz/host/glim.sh/llms.txt)