Safety

Analyze image for visual and textual safety concerns

Upload an image (png, jpg, gif, webp — max 10MB) for dual-layer analysis: Vision AI classifies visual content (nudity, violence, weapons, drugs, self-harm imagery) while OCR extracts embedded text for separate safety analysis. Returns visual categories, extracted text, face detection, and combined overall risk score. Covers screenshots, memes, shared photos, and profile images.

post/api/v1/safety/image

Request

  • Base URL: https://api.tuteliq.ai
  • URL: https://api.tuteliq.ai/api/v1/safety/image
  • Auth: one of:
    • HTTP bearer
    • API key in header x-api-key

Response

Default Response

file_idstring
text_analysisobject
overall_risk_scorenumber
overall_severity'none' | 'low' | 'medium' | 'high' | 'critical'
detectedboolean

A concern was observed at ANY severity, including monitor-only cases. For production branching prefer recommended_action.

confidencenumber

Confidence in the overall verdict (0-1).

recommended_action'none' | 'monitor' | 'flag_for_review' | 'block' | 'immediate_intervention'

Routing key, weakest to strongest: none, monitor, flag_for_review, block, immediate_intervention. Derived from the stronger of the visual verdict and the OCR text verdict, so harmful text in a visually benign image still routes correctly. Safe to switch on.

action_detailstring

Human-readable expansion of recommended_action for a moderator UI. Free text: do not branch on it.

rationalestring

Why this verdict was reached. Built from category and severity labels only; never contains the image description or its extracted text.

credits_usednumber

Number of credits consumed by this request

external_idstring
incident_moderation_enabledstring

Per-call override of account incident logging: "true" forces persistence, "false" suppresses it. Omit for account default.

customer_idstring
metadataobject

Echo of the metadata you provided in the request

Changes

No recorded changes to this operation across all 1 revision of this API.