AI Image Detection API for agent workflows.

Try the image demo

Use the sample fixture or paste a public HTTPS image URL. Demo requests are rate limited and force store_content:false.

{
  "recommended_action": "human_review",
  "risk_level": "high",
  "primary_reason": "visible synthetic-media cues"
}

FAQ

Can VeracityAPI detect AI-generated images?

It can flag visible synthetic-media cues as probabilistic workflow-risk signals. It does not prove generation or authorship.

Does it identify people or brands?

No. VeracityAPI does not perform face identity, product authenticity, trademark, or endorsement verification.

Do you store the image?

No raw image bytes or full image URLs are stored. Logs keep metadata such as hostname and URL hash.

How should high-risk image results be routed?

Queue for human review, request source/provenance, or quarantine the upload depending on your local policy.

Copy-paste routing example

curl https://api.veracityapi.com/v1/analyze \
  -H "Authorization: Bearer $VERACITY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "type": "image",
    "content": "https://veracityapi.com/demo/influencer-beauty-tonic.jpg",
    "context": {
      "format": "social_post",
      "intended_use": "publish",
      "domain": "image UGC moderation"
    },
    "store_content": false
  }'

Agent policy

Submit an HTTPS image URL; receive synthetic_image_risk, evidence, content_trust_score, risk_level, and recommended_action. Use the action field to route uploads, not to accuse people.