Skip to main content
POST
Tag an image

Authorizations

API-Key
string
header
required

Body

multipart/form-data
image
file
required

Binary image file to analyze. Use this or image_url, but not both.

image_url
string<uri>

Publicly reachable image URL to analyze instead of uploading a file.

lang
string
default:en

Language used for language-dependent outputs such as caption or keywords.

Example:

"en"

mode
string
default:editorial

Tagging profile. Currently the default documented mode is editorial.

Example:

"editorial"

date
string
default:""

Optional image context date, typically in ISO format YYYY-MM-DD. Helps downstream people and caption enrichment.

Example:

"2025-10-16"

event
string
default:""

Optional event name associated with the image, used as context for enriched outputs.

Example:

"Carabao Cup winners presentation"

city
string
default:""

Optional city associated with the image context.

Example:

"London"

country
string
default:""

Optional country associated with the image context.

Example:

"United Kingdom"

caption
boolean
default:false

When true, include an AI-generated caption in the response.

keywords
boolean
default:false

When true, include generated keyword tags in the response.

ocr
boolean
default:false

When true, include OCR text extracted from the image.

colors
boolean
default:false

When true, include dominant colors and black-and-white detection.

Response

Successful Response

height
integer | null

Image height in pixels.

width
integer | null

Image width in pixels.

ratio
number | null

Aspect ratio of the image.

orient
string | null

Image orientation.

n_faces
integer | null

Number of detected faces.

shot
string | null

Predicted shot type.

illumination
string | null

Predicted lighting type.

shape

Predicted image shape/style or raw shape dimensions.

date

Image date when available.

people
TagPersonResponse · object[] | null

Detected people metadata.

photo_or_illus
string | null

Whether the input is a photo or illustration.

type_of_photo
string | null

Predicted photo subtype.

type_of_illus
string | null

Predicted illustration subtype.

categories
string[] | null

General image categories.

colors
string[] | null

Representative image colors when requested.

bw
boolean | null

Whether the image is black and white.

caption
string | null

Generated caption when requested.

keywords
string[] | null

Generated keywords when requested.

ocr
string | null

Extracted OCR text when requested.