> ## Documentation Index
> Fetch the complete documentation index at: https://docs.deepface.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Read model and detector capabilities



## OpenAPI

````yaml /openapi/deepface.openapi.yaml get /capabilities
openapi: 3.1.0
info:
  title: deepface.dev API
  version: v1
  summary: Managed API for face verification, embeddings, and vector comparison.
  description: >
    Canonical OpenAPI contract for the public deepface.dev gateway. This covers
    the public surface: health, capabilities, verify, represent, and compare.
  license:
    name: Proprietary
    url: https://deepface.dev/terms
servers:
  - url: https://api.deepface.dev
    description: Production gateway
security:
  - BearerAuth: []
  - ApiKeyHeader: []
tags:
  - name: Service
    description: Read-only service metadata and health routes.
  - name: Compute
    description: Authenticated face verification and vector-comparison endpoints.
paths:
  /capabilities:
    get:
      tags:
        - Service
      summary: Read model and detector capabilities
      operationId: getCapabilities
      responses:
        '200':
          description: Active allowlists and defaults
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CapabilitiesResponse'
        '404':
          $ref: '#/components/responses/NotFound'
        '502':
          $ref: '#/components/responses/UpstreamError'
      security: []
components:
  schemas:
    CapabilitiesResponse:
      type: object
      required:
        - allowed_models
        - default_model
        - allowed_detectors
        - default_detector
      properties:
        allowed_models:
          type: array
          items:
            type: string
        default_model:
          type: string
        allowed_detectors:
          type: array
          items:
            type: string
        default_detector:
          type: string
    ErrorResponse:
      type: object
      description: >
        Gateway errors include `upstream_response_too_large` when the model
        response exceeds the configured gateway response-size limit.
      required:
        - error
      properties:
        error:
          type: string
        detail:
          type: string
  responses:
    NotFound:
      description: Route does not exist
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    UpstreamError:
      description: Model server request failed
      headers:
        x-request-id:
          $ref: '#/components/headers/RequestId'
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
  headers:
    RequestId:
      description: Request identifier echoed by the gateway.
      schema:
        type: string
        format: uuid
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API key
      description: Use your API key as a bearer token.
    ApiKeyHeader:
      type: apiKey
      in: header
      name: x-api-key
      description: Alternative header for API key authentication.

````