# StableDetect Image/Deepfake Detection

> StableDetect Image/Deepfake Detection is a paid API for AI agents from stabledetect.dev, paid per call via x402, $0.02/call, status down (last checked 2026-09-15).

Classifies a submitted image or video as AI-generated, deepfake, or human-authentic using pay-per-call detection.

## Facts

- Endpoint: POST https://stabledetect.dev/api/detect/image
- Price: $0.02/call
- Payment: x402
- Status: down
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/stabledetect-image-deepfake-detection-4f5d9532
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_j5ow53T_pPbAWWL_tPGXn

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 stabledetect-image-deepfake-detection-4f5d9532 -d '<json body>'
```

Example prompt: Can you check if this image is AI-generated or a deepfake? Here's the file — I need to know if it's real or synthetic, and how confident the detection is.

## When to prefer this

Use this endpoint when you need to verify whether a specific image or video is AI-generated or a deepfake, especially in workflows requiring media authenticity checks such as identity verification, content moderation, or disinformation detection. Prefer this over text-detection endpoints when the input is visual media rather than text.

## Known failure modes

- Invalid or unreadable image format returns an error
- Unsupported media type (e.g. non-image file) rejected
- Payment failure or insufficient USDC balance causes 402 response
- Image URL inaccessible or timed out
- Image too large or resolution out of supported range
- Ambiguous result when image is partially AI-edited

## How this service works

Pay-per-call AI content detection. Classify text as AI-generated, AI-assisted, or human-written, and detect AI-generated or deepfake images and video.

## Output

Returns a classification of the image as AI-generated, deepfake, or human-authentic, along with a confidence score or probability indicating how likely the image is synthetic or manipulated.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method",
    "bodyType",
    "body"
   ],
   "properties": {
    "body": {
     "type": "object",
     "$schema": "https://json-schema.org/draft/2020-12/schema",
     "required": [
      "image"
     ],
     "properties": {
      "image": {
       "type": "string",
       "maxLength": 10000000,
       "minLength": 1,
       "description": "Image to analyze. Either a public http(s) URL or a data URL (data:image/png;base64,...). Supported formats: JPEG, PNG, GIF, BMP, WebP, AVIF. The URL must allow automated downloads — hosts that block bots (e.g. upload.wikimedia.org) return 400; use a data URL for those."
      }
     },
     "additionalProperties": false
    },
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "POST",
      "PUT",
      "PATCH"
     ],
     "type": "string"
    },
    "bodyType": {
     "enum": [
      "json",
      "form-data",
      "text"
     ],
     "type": "string"
    }
   },
   "additionalProperties": false
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/stabledetect-image-deepfake-detection-4f5d9532/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from stabledetect.dev](https://www.zero.xyz/host/stabledetect.dev/llms.txt)