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

# Get platform capabilities

> Retrieves platform capabilities for the current deployment instance.
Returns the list of available LLM models and IVR voice recognition availability.
Each model includes a provider field and a deprecated flag.
This endpoint is publicly accessible and does not require authentication.
IVR voice recognition availability requires an authenticated context; without auth it defaults to false.



## OpenAPI

````yaml https://blackbox.dasha.ai/swagger/v1/swagger.json get /api/v1/misc/capabilities
openapi: 3.0.4
info:
  title: Dasha BlackBox Agent API
  description: API for managing AI agents and calls
  contact:
    name: DashaAI Team
    email: support@dasha.ai
  version: v1
servers:
  - url: https://blackbox.dasha.ai
    description: Dasha BlackBox Agent API
security:
  - ApiKey: []
  - OAuth: []
tags:
  - name: ActivityLogs
  - name: Agents
  - name: AgentTestCases
  - name: CallResults
  - name: Calls
  - name: Chats
  - name: Copilot
  - name: CustomerData
  - name: Mcp
  - name: Media
  - name: Misc
  - name: PronunciationDictionaries
  - name: Providers
  - name: SipAliases
  - name: SipCredentials
  - name: SipPhoneNumbers
  - name: TextChat
  - name: TwilioProvider
  - name: Voice
  - name: WebhookTest
  - name: WebIntegrations
  - name: WebSocket
    description: WebSocket endpoints for real-time communication
paths:
  /api/v1/misc/capabilities:
    get:
      tags:
        - Misc
      summary: Get platform capabilities
      description: >-
        Retrieves platform capabilities for the current deployment instance.

        Returns the list of available LLM models and IVR voice recognition
        availability.

        Each model includes a provider field and a deprecated flag.

        This endpoint is publicly accessible and does not require
        authentication.

        IVR voice recognition availability requires an authenticated context;
        without auth it defaults to false.
      responses:
        '200':
          description: Returns platform capabilities successfully
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/MiscCapabilitiesDto'
        '500':
          description: Server error occurred while retrieving capabilities
components:
  schemas:
    MiscCapabilitiesDto:
      required:
        - copilotPossible
        - emulationTestsPossible
        - ivrVoiceRecognitionPossible
        - llmModels
        - noiseSuppressionTypes
      type: object
      properties:
        ivrVoiceRecognitionPossible:
          type: boolean
          description: >-
            Indicates whether IVR voice recognition is available for the
            organization. When true, the organization can enable IVR voice
            recognition in agent voicemail handling configuration. Availability
            depends on both the deployment environment and the organization's
            feature flag status.
        llmModels:
          type: array
          items:
            $ref: '#/components/schemas/LLMModelDto'
          description: >-
            List of LLM models available for selection.

            Each model includes a provider field and a deprecated flag.

            The frontend must render only these models in the specified order
            and never use a hardcoded list.
        noiseSuppressionTypes:
          type: array
          items:
            $ref: '#/components/schemas/NoiseSuppressionType'
          description: >-
            List of noise suppression types available for the organization.

            Empty array means noise suppression is not available.

            Contains the allowed engine types (e.g., "none", "krisp") when the
            organization has access.
        copilotPossible:
          type: boolean
          description: >-
            Indicates whether the AI assistant (copilot) is available for the
            organization. When true, the organization can use the assistant.
            Availability depends on the organization's feature flag status; an
            unauthenticated request always sees false.
        emulationTestsPossible:
          type: boolean
          description: >-
            Indicates whether agent emulation tests are available for the
            organization. When true, the organization can create and run
            end-to-end tests for its agents. Availability depends on the
            organization's feature flag status; an unauthenticated request
            always sees false.
      additionalProperties: false
      description: Platform capabilities available for the current deployment instance.
    LLMModelDto:
      required:
        - costTier
        - deprecated
        - description
        - displayName
        - displayOrder
        - id
        - provider
      type: object
      properties:
        id:
          minLength: 1
          type: string
          description: The model identifier used in API calls (e.g., "gpt-4.1-mini").
        displayName:
          minLength: 1
          type: string
          description: Human-readable display name shown in the UI (e.g., "GPT-4.1 Mini").
        description:
          minLength: 1
          type: string
          description: Short description of the model's characteristics and best use cases.
        costTier:
          minLength: 1
          type: string
          description: 'Relative cost tier for the model: "low", "medium", or "high".'
        displayOrder:
          type: integer
          description: Sort order for display in the dropdown (lower values appear first).
          format: int32
        deprecated:
          type: boolean
          description: >-
            Whether this model is deprecated and no longer recommended for new
            agents.

            Agents using deprecated models continue working, but the UI shows a
            deprecation badge.
        provider:
          minLength: 1
          type: string
          description: The LLM provider for this model (e.g., "openai", "anthropic").
      additionalProperties: false
      description: |-
        Metadata for a single LLM model exposed via capabilities.
        Generic across providers (OpenAI, Anthropic, etc.).
    NoiseSuppressionType:
      enum:
        - none
        - krisp
      type: string
      description: The noise suppression engine type.
  securitySchemes:
    ApiKey:
      type: http
      description: API Key Authentication (Bearer {key})
      scheme: Bearer
    OAuth:
      type: oauth2
      flows:
        implicit:
          authorizationUrl: https://auth.dasha.ai/connect/authorize
          scopes:
            platform_api: Platform API

````