Skip to main content
POST
JavaScript

Autorizzazioni

Authorization
string
header
obbligatorio

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

Corpo

application/json

A screen of text, an image, or both. Send at least one of text and image.

image
string | null

The image to screen, as base64, with or without a data:image/...;base64, prefix. The formats are JPEG, PNG, WebP, GIF and BMP. The limit is 6991530 base64 characters, and the decoded image must be at most 5 MiB.

Maximum string length: 6991530
request_id
string | null

Your identifier for this screen, up to 128 characters, with no control characters. The response returns it in request_id.

text
string | null

The text to screen, up to 8000 characters.

Maximum string length: 8000

Risposta

The verdict.

The verdict of one screen.

categories
object
obbligatorio

The probability, from 0 to 1, that the screen falls in each category.

compound_triggered
boolean
obbligatorio

True when real-person likeness and sexual content together crossed their combined threshold, the pattern of a sexual deepfake.

decision
enum<string>
obbligatorio

The verdict. allow means the content passed. deny means block the content. flag means apply your own judgement. It is not a soft deny.

Opzioni disponibili:
allow,
flag,
deny
latency_ms
integer<int64>
obbligatorio

The time the screen took, in milliseconds.

Intervallo richiesto: x >= 0
normalized_applied
boolean
obbligatorio

True when the text was also screened in a normalized form, with obfuscation such as invisible or look-alike characters removed.

notes
string[]
obbligatorio

Human-readable reasons for the decision. The wording can change, so do not parse it.

passes
integer<int64>
obbligatorio

The number of yes/no questions the model answered for this screen.

Intervallo richiesto: x >= 0
provenance
object
obbligatorio

How each score in categories was measured.

request_id
string | null
obbligatorio

The request_id you sent, or null.

triggered
enum<string>[]
obbligatorio

The categories whose score crossed the threshold of the category. It can be empty on a flag from the general check. notes then gives the reason.

A moderation category.

Opzioni disponibili:
violent_crimes,
sex_related_crimes,
child_sexual_exploitation,
suicide_and_self_harm,
indiscriminate_weapons,
intellectual_property,
defamation,
non_violent_crimes,
hate,
privacy,
specialized_advice,
sexual_content,
non_consensual_intimate_imagery,
minor_coded_language,
real_person_likeness,
living_artist_style,
prompt_injection
Ultima modifica il 26 settembre 2026