Scam AI raised $2.6M to combat AI-powered scams→
scam.ai

~/docs cat detect-image.md

Detect an image

Checks a photo or a still image for AI generation and editing, and answers with one verdict and one score for the whole image.

Send the file

curl -X POST \
  "https://api.scam.ai/v1/detections" \
  -H "x-api-key: <YOUR_API_KEY>" \
  -F "file=@/path/to/photo.jpg"

Images are sent as a file. A link to an image is fetched too; see Detect from a link.

Parameters

Request parameters
FieldTypeMeaning
filebinaryThe media file. JPG, PNG or WEBP; HEIC is not accepted, at most 10 MB (on Eva V1.5, the default, also every side under 3840 px).

The response

idstring
The detection id. Pass it to GET /v1/detections/{id} to read the run back.
statusstring
Always "completed". The answer arrives in the same request.
created_atstring
When the run finished. RFC 3339, millisecond precision, always Z.
mediaobject
What was checked: type (image, video or audio), filename, mime_type and bytes. The last three can be null when they were not known. mime_type is what the upload declared, so a client that sends no content type sees application/octet-stream here; type comes from the bytes themselves.
modelstring
The Eva version that answered this run, "Eva V1.5" or "Eva V1.6". Which version answers is set per account.
verdictstring
LIKELY_REAL, ALERT or LIKELY_AI. Branch on this.
scorenumber | null
0 to 1, the probability the media is AI-made or manipulated. null when nothing could be scored.
summarystring
One sentence a person can read, matching the verdict.
credits_usednumber
What this run cost, an integer. 0 on a sandbox key, or when the same file was sent byte for byte from this account within 30 days.
zero_charge_reasonstring
Only when credits_used is 0: "sandbox" or "duplicate".
response · 200
{  "id": "6f1c2a3e-9b7d-4e5f-8a21-3c4d5e6f7a8b",  "status": "completed",  "created_at": "2026-09-15T10:12:33.123Z",  "media": {    "type": "image",    "filename": "photo.jpg",    "mime_type": "image/jpeg",    "bytes": 248113  },  "model": "Eva V1.6",  "verdict": "LIKELY_AI",  "score": 0.92,  "summary": "This image shows strong signs of being AI-generated or edited.",  "credits_used": 1}

Questions

Why did I get a 422 instead of a verdict?
For an image it usually means the bytes did not decode, the format is not supported, or the image is larger than the detector accepts (IMAGE_TOO_LARGE: on Eva V1.5, the default, an edge of 3840 px or more, so send a smaller copy). The body carries a stable error.code; a refusal that names the content carries reasons[], such as no_face on an image or no_voice_content on audio. Show it to your user; do not retry the same file. Nothing is charged. See Errors.
Do you keep the image?
Yes. Every run keeps the file and a history row, so it can be read back by id. Retention is covered by the privacy policy and DPA.
← Which input do I send?Detect a video →

Start building

Create an API key in the dashboard and send your first file. To go through an integration or an on-prem deployment with our team, request a demo.

Get an API keyRequest a demo