Skip to main content
POST
Check image rights

Authorizations

Authorization
string
header
required

API key starting with zt_live_ (production) or zt_test_ (sandbox). Get your key at https://developers.zebratruth.ai

Headers

Idempotency-Key
string<uuid>
required

Unique request identifier to prevent duplicate execution and double-charging. Generate a new UUID for each distinct request. Reuse the same key to safely retry.

Body

Image checks do not run the financial-services specialists. Sending reviewScopes or contentKind returns 400 review_scope_not_enabled.

imageUrls
string<uri>[]
required

Image URLs to check (max 2 per request)

Maximum array length: 2
jurisdictions
enum<string>[]
required
Available options:
us,
eu,
uk,
india,
china
platforms
enum<string>[]
required
Available options:
youtube,
instagram,
facebook,
tiktok,
linkedin

Response

Image compliance results

checks
object[]

All compliance checks emitted for the image(s). Each carries status, severity, message, recommendation, and citation.

checksById
object

Same checks keyed by id for direct lookup.

indexes
object

Inverted indexes (byStatus, bySeverity, byJurisdiction, byPlatform, byCategory) for convenient UI filtering.

annotations
object[]

image-region annotations with bounding boxes for detected elements, when the underlying detection produces one.

decision
enum<string>

Canonical compliance decision aggregated from check severities:

  • PUBLISH — clean (green light)
  • HOLD — review needed (yellow light)
  • BLOCK — do not publish (red light)
Available options:
PUBLISH,
HOLD,
BLOCK
Example:

"BLOCK"

score
number

Compliance score (0–100, higher is better). Driven by aggregated check severities. Below 50 typically maps to BLOCK.

Required range: 0 <= x <= 100
Example:

22

cached
boolean

Whether the result came from the request cache (identical inputs within the cache window).

Example:

false

creditsCharged
number

Credits debited from the tenant balance for this request. Scales linearly with imageCount.

costBreakdown
object

Per-agent credit + latency breakdown.