Skip to main content
POST
/
v2
/
advanced-image-detection
cURL
curl --request POST \
  --url https://api.gowinston.ai/v2/advanced-image-detection \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "image_url": "https://example.com/image.png"
}
'
{
  "status": 200,
  "cost": 500,
  "language": "en",
  "title": "Portrait of a Person",
  "tags": [
    "portrait",
    "face"
  ],
  "tool_used": [
    "classify_image",
    "extract_metadata",
    "ela_image"
  ],
  "label": "AI-Generated",
  "confidence": "High",
  "authenticity": "Manipulated",
  "conclusion": "The image shows strong indicators of AI generation.",
  "analysis": "<string>",
  "tools_used_analysis": [
    {
      "id": "extract_metadata",
      "analysis": "The metadata is stripped of EXIF and C2PA information.",
      "result": {}
    }
  ],
  "balance": 9500
}

Documentation Index

Fetch the complete documentation index at: https://docs.gowinston.ai/llms.txt

Use this file to discover all available pages before exploring further.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

The Advanced Image Detection request body

​
image_url
string
required

Public HTTP or HTTPS URL of the image to analyze. The API rejects empty values, non-string values, URLs without a hostname, URLs with embedded credentials, localhost, .localhost, and direct private or reserved IP addresses.

Example:

"https://example.com/image.png"

Response

Advanced Image Detection response

​
status
integer

Internal analysis status from the image analysis pipeline. The external HTTP status for a successful API request is 200 OK.

Example:

200

​
cost
integer

Number of credits charged for this API request. Current value is 500.

Example:

500

​
language
string

Language used for the generated analysis text.

Example:

"en"

​
title
string

Short generated title describing the analyzed image.

Example:

"Portrait of a Person"

​
tags
string[]

Tags extracted or inferred from the image metadata and analysis pipeline.

Example:
["portrait", "face"]
​
tool_used
string[]

List of internal forensic tool IDs used during the analysis. Possible values include classify_image, extract_metadata, ela_image, residual_noise_maps, edge_anomaly_heat_map, and cfa_pattern_analysis.

Example:
[
  "classify_image",
  "extract_metadata",
  "ela_image"
]
​
label
enum<string>

Final classification label for the image.

Available options:
AI-Generated,
Human
Example:

"AI-Generated"

​
confidence
enum<string>

Confidence level for the final classification.

Available options:
High,
Moderate,
Low
Example:

"High"

​
authenticity
enum<string>

Final authenticity assessment.

Available options:
Authentic,
Manipulated
Example:

"Manipulated"

​
conclusion
string

Short final conclusion summarizing the forensic result.

Example:

"The image shows strong indicators of AI generation."

​
analysis
string

Complete human-readable forensic analysis, including a summary of the tools used and their findings.

​
tools_used_analysis
object[]

Per-tool analysis results. Each item contains the tool ID, a generated explanation of that tool's result, and the underlying tool output.

​
balance
integer

User's remaining credit balance after the successful request is charged.

Example:

9500