▣ ARTIFICIAL INTELLIGENCE · IMAGE PROCESSING

AI Video Face Detection API

Hosted on ApyHub

What it does

Face Detection lets you send an image or video URL and get face-detection results back from either Azure or Google, depending on the provider you select.

Use the /file endpoint to upload a file, or the /url endpoint to point the service at a remote asset. In both cases, the request requires requested_service, which must be azure or google. The file-based route also accepts azure_region, azure_account_id, azure_access_token, and google_credential_file where relevant. The URL route accepts a url, plus provider-specific fields under azure or google, including Google credential JSON when you are using the Google route.

The response wraps results under data, with either an azure object or a google object present depending on the selected service. That makes it straightforward to plug Face Detection into moderation flows, media indexing, or any workflow that needs to detect faces before you store, route, or analyse visual content.

If you are building an app that handles user uploads or remote media links, Face Detection gives you a simple way to separate the transport layer from the detection provider while keeping the contract clear on both sides.

Provider (requested_service)	Atoms
Azure	500
Google	500

▣ ENDPOINT 01 / 02

POST

Face Detection via file upload

https://api.eu.apyhub.com/apyhub/face-detection/file

QUICKSTART

GUIDE

Quickstart

Upload a face image and request the Azure service.

curl -X POST "https://api.eu.apyhub.com/apyhub/face-detection/file" \
  -H "apy-token: $APY_TOKEN" \
  -F "file=@/path/to/face-image.jpg" \
  -F "requested_service=azure" \
  -F 'azure_access_token="your-azure_access_token"' \
  -F 'azure_account_id="your-azure_account_id"' \
  -F 'azure_region="your-azure_region"'

What you'll get back

Returns a JSON object with a data object. When requested_service is azure, the data object may include an azure object with the detection result.

{
  "data": {
    "azure": {}
  }
}

TRY ITLIVE · 500 ATOMS

API key

Loading your default key…

The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.

Max 100MB total per request (all files combined). Larger? Use this API's URL-based endpoint instead, if it has one.

About this endpoint

What it does

Detects faces from an uploaded file and routes the request to either Azure or Google based on requested_service. The response returns a JSON object with a data object containing provider-specific results.

Request Body

Parameter	Type	Description
file	Binary	Uploaded file to analyze. Binary format.
azure_region	String	Azure region.
azure_account_id	String	Azure account ID.
requested_service	ENUM	Route to use for detection. Allowed values: `azure`, `google`.
azure_access_token	String	Azure access token.
google_credential_file	Binary	Google service account JSON file. Binary format.

Response

Returns a JSON object with a required data object field. Inside data, the schema defines optional azure and google object fields; the relevant one is present depending on the selected requested_service.

Parameter	Type	Description
data	Object	Response wrapper object. Contains provider-specific result fields.
data.azure	Object	Present when `requested_service` is `azure`. Additional properties are allowed.
data.google	Object	Present when `requested_service` is `google`. Additional properties are allowed.

Max 100MB total per request (all files combined). Larger? Use this API's URL-based endpoint instead, if it has one.

▣ ENDPOINT 02 / 02

POST

Face Detection via URL

https://api.eu.apyhub.com/apyhub/face-detection/url

QUICKSTART

GUIDE

Quickstart

Detect faces in an image or video URL with the Azure face-detection service.

curl -X POST "https://api.eu.apyhub.com/apyhub/face-detection/url" \
  -H "apy-token: $APY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://assets.apyhub.com/samples/sample.mp4",
    "requested_service": "azure",
    "azure": {
        "access_token": "your-access_token",
        "account_id": "your-account_id",
        "region": "your-region"
    }
  }'

What you'll get back

Returns a JSON object with a data object. When requested_service is azure, data.azure is present; when requested_service is google, data.google is present.

{
  "data": {
    "azure": {}
  }
}

TRY ITLIVE · 500 ATOMS

API key

Loading your default key…

The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.

About this endpoint

What it does

Detects faces in a media file fetched from a URL. You send the media URL and choose which service to use with requested_service; the response returns a JSON object with a data object containing the service-specific result.

Request Body

Parameter	Type	Description
url	String	URL of the media to analyze. Must be a URI.
azure	Object	Azure-specific configuration object. Includes `region`, `account_id`, and `access_token` if you are using the Azure service.
azure.region	String	Azure region.
azure.account_id	String	Azure account ID.
azure.access_token	String	Azure access token.
google	Object	Google-specific configuration object. Includes `google_language` and `google_credential_json` if you are using the Google service.
google.google_language	String	Google language code.
google.google_credential_json	Object	Google Cloud service account JSON. Required for Google video routes. See schema for nested fields.
requested_service	ENUM	Service to use. Allowed values: `azure`, `google`.

Response

Returns a JSON object with a required data object field. The data object may contain an azure object when requested_service is azure, or a google object when requested_service is google.

Parameter	Type	Description
data	Object	Response wrapper. May include `azure` and/or `google` result objects depending on the requested service.

Notes

The response schema only guarantees that data.azure is present when requested_service is azure, and data.google is present when requested_service is google; both service result objects are free-form (additionalProperties: true), so their exact fields are not defined here.

▣ COMMON ERRORS

Errors any endpoint can return

400bad_request

Required parameter missing or malformed body.

401unauthorized

API key missing, revoked, or not authorized for this service.

429rate_limited

Your plan's per-second rate exceeded. Retry with exponential backoff.

503upstream_busy

Backend temporarily unavailable. Try again in a few seconds.

Similar APIs

Closest matches in the catalog based on this service.

CALLAI Image Face Detection APIApyHub CALLAI Video Object Detection APIApyHub CALLAI Video Person Detection APIApyHub CALLAI Video Label Detection APIApyHub

From the blog

Reads that touch this API.

Dynamic pricing: every API call costs what the work actually costsAug 20, 2026 Face Detection using AI: Use Cases, Benefits, and ImplementationJul 9, 2026 Changelog: 07 March 2024 - New APIs, Updates and moreJul 9, 2026 ApyHub Changelog – 10 Jan 2024: New APIs & More Jul 9, 2026