Deepgram

Deepgram Models API

Retrieve available model metadata.

GitHub OpenAPI

Operations 5

GET /v1/agent/settings/think/models List Agent Think Models #
GET /v1/projects/{project_id}/models List Project Models #
GET /v1/projects/{project_id}/models/{model_id} Get a Project Model #
GET /v1/models List Models #
GET /v1/models/{model_id} Get a specific Model #

Documentation

📖
Documentation
https://developers.deepgram.com/docs/stt/getting-started
📖
Documentation
https://developers.deepgram.com/reference/text-to-speech-api/speak
📖
Documentation
https://developers.deepgram.com/docs/audio-intelligence
📖
Documentation
https://developers.deepgram.com/docs/create-additional-api-keys

Specifications

⚙
OpenAPI
https://artifacts.apis.io/deepgram/openapi/deepgram-models-api-openapi.yml
⚙
AsyncAPI
https://artifacts.apis.io/deepgram/asyncapi/deepgram-speech-to-text-asyncapi.yml
⚙
AsyncAPI
https://artifacts.apis.io/deepgram/asyncapi/deepgram-text-to-speech-asyncapi.yml

Other Resources

🔗
Rules
https://artifacts.apis.io/deepgram/rules/deepgram-speech-to-text-api-rules.yml
🔗
Rules
https://artifacts.apis.io/deepgram/rules/deepgram-text-to-speech-api-rules.yml
🔗
Rules
https://artifacts.apis.io/deepgram/rules/deepgram-management-api-rules.yml

Work with this as data

Every API here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for apis

7 MCP tools reach this
  • find_apisBrowse and filter every API in the catalog.
  • get_api_artifactsOne API's artifacts, grouped by type.
  • get_openapiThe primary OpenAPI for this API.
  • find_similar_apisAPIs that look like this one.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This API 
curl "https://apis.io/api/v1/apis/deepgram:deepgram-models-api"
All apis 
curl "https://apis.io/api/v1/apis?limit=25"

Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.

OpenAPI Specification

deepgram-models-api-openapi.yml Raw ↑ 
openapi: 3.2.0
info:
  title: REST Models API
  version: 1.0.0
servers:
- url: https://agent.deepgram.com
  description: Production
- url: https://api.deepgram.com
  description: Base
tags:
- name: Models
paths:
  /v1/agent/settings/think/models:
    get:
      operationId: models_list
      summary: List Agent Think Models
      description: Retrieves the available think models that can be used for AI agent processing
      tags:
      - Models
      responses:
        '200':
          description: List of available think models
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AgentThinkModelsV1Response'
        '400':
          description: Invalid Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
  /v1/projects/{project_id}/models:
    get:
      operationId: models_list_2
      summary: List Project Models
      description: Returns metadata on all the latest models that a specific project has access to, including non-public models
      tags:
      - Models
      parameters:
      - name: project_id
        in: path
        description: The unique identifier of the project
        required: true
        schema:
          type: string
      - name: include_outdated
        in: query
        description: returns non-latest versions of models
        required: false
        schema:
          type: boolean
      responses:
        '200':
          description: A list of models
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListModelsV1Response'
        '400':
          description: Invalid Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      security:
      - ApiKeyAuth: []
  /v1/projects/{project_id}/models/{model_id}:
    get:
      operationId: models_get
      summary: Get a Project Model
      description: Returns metadata for a specific model
      tags:
      - Models
      parameters:
      - name: project_id
        in: path
        description: The unique identifier of the project
        required: true
        schema:
          type: string
      - name: model_id
        in: path
        description: The specific UUID of the model
        required: true
        schema:
          type: string
      responses:
        '200':
          description: A model object that can be either STT or TTS
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetModelV1Response'
        '400':
          description: Invalid Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      security:
      - ApiKeyAuth: []
  /v1/models:
    get:
      operationId: models_list_3
      summary: List Models
      description: Returns metadata on all the latest public models. To retrieve custom models, use Get Project Models.
      tags:
      - Models
      parameters:
      - name: include_outdated
        in: query
        description: returns non-latest versions of models
        required: false
        schema:
          type: boolean
      responses:
        '200':
          description: A list of models
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ListModelsV1Response'
        '400':
          description: Invalid Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      security:
      - ApiKeyAuth: []
  /v1/models/{model_id}:
    get:
      operationId: models_get_2
      summary: Get a specific Model
      description: Returns metadata for a specific public model
      tags:
      - Models
      parameters:
      - name: model_id
        in: path
        description: The specific UUID of the model
        required: true
        schema:
          type: string
      responses:
        '200':
          description: A model object that can be either STT or TTS
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/GetModelV1Response'
        '400':
          description: Invalid Request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      security:
      - ApiKeyAuth: []
components:
  schemas:
    AgentThinkModelsV1ResponseModelsItemsOneOf2Id:
      type: string
      enum:
      - gemini-2.5-flash
      - gemini-2.0-flash
      - gemini-2.0-flash-lite
      description: The unique identifier of the Google model
      title: AgentThinkModelsV1ResponseModelsItemsOneOf2Id
    AgentThinkModelsV1ResponseModelsItems0:
      type: object
      properties:
        id:
          $ref: '#/components/schemas/AgentThinkModelsV1ResponseModelsItemsOneOf0Id'
          description: The unique identifier of the OpenAI model
        name:
          type: string
          description: The display name of the model
        provider:
          description: The provider of the model
      required:
      - id
      - name
      - provider
      description: OpenAI models
      title: AgentThinkModelsV1ResponseModelsItems0
    ListModelsV1Response:
      type: object
      properties:
        stt:
          type: array
          items:
            $ref: '#/components/schemas/ListModelsV1ResponseSttModels'
        tts:
          type: array
          items:
            $ref: '#/components/schemas/ListModelsV1ResponseTtsModels'
      title: ListModelsV1Response
    AgentThinkModelsV1Response:
      type: object
      properties:
        models:
          type: array
          items:
            $ref: '#/components/schemas/AgentThinkModelsV1ResponseModelsItems'
      required:
      - models
      title: AgentThinkModelsV1Response
    AgentThinkModelsV1ResponseModelsItems3:
      type: object
      properties:
        id:
          $ref: '#/components/schemas/AgentThinkModelsV1ResponseModelsItemsOneOf3Id'
          description: The unique identifier of the Groq model
        name:
          type: string
          description: The display name of the model
        provider:
          description: The provider of the model
      required:
      - id
      - name
      - provider
      description: Groq models
      title: AgentThinkModelsV1ResponseModelsItems3
    GetModelV1Response1:
      type: object
      properties:
        name:
          type: string
        canonical_name:
          type: string
        architecture:
          type: string
        languages:
          type: array
          items:
            type: string
        version:
          type: string
        uuid:
          type: string
          format: uuid
        metadata:
          $ref: '#/components/schemas/GetModelV1ResponseOneOf1Metadata'
      title: GetModelV1Response1
    GetModelV1Response:
      oneOf:
      - $ref: '#/components/schemas/GetModelV1Response0'
      - $ref: '#/components/schemas/GetModelV1Response1'
      title: GetModelV1Response
    GetModelV1Response0:
      type: object
      properties:
        name:
          type: string
        canonical_name:
          type: string
        architecture:
          type: string
        languages:
          type: array
          items:
            type: string
        version:
          type: string
        uuid:
          type: string
          format: uuid
        batch:
          type: boolean
        streaming:
          type: boolean
        formatted_output:
          type: boolean
      title: GetModelV1Response0
    AgentThinkModelsV1ResponseModelsItemsOneOf0Id:
      type: string
      enum:
      - gpt-5
      - gpt-5-mini
      - gpt-5-nano
      - gpt-4.1
      - gpt-4.1-mini
      - gpt-4.1-nano
      - gpt-4o
      - gpt-4o-mini
      description: The unique identifier of the OpenAI model
      title: AgentThinkModelsV1ResponseModelsItemsOneOf0Id
    AgentThinkModelsV1ResponseModelsItems1:
      type: object
      properties:
        id:
          $ref: '#/components/schemas/AgentThinkModelsV1ResponseModelsItemsOneOf1Id'
          description: The unique identifier of the Anthropic model
        name:
          type: string
          description: The display name of the model
        provider:
          description: The provider of the model
      required:
      - id
      - name
      - provider
      description: Anthropic models
      title: AgentThinkModelsV1ResponseModelsItems1
    ListModelsV1ResponseTtsModels:
      type: object
      properties:
        name:
          type: string
        canonical_name:
          type: string
        architecture:
          type: string
        languages:
          type: array
          items:
            type: string
        version:
          type: string
        uuid:
          type: string
          format: uuid
        metadata:
          $ref: '#/components/schemas/ListModelsV1ResponseTtsModelsMetadata'
      title: ListModelsV1ResponseTtsModels
    ListModelsV1ResponseSttModels:
      type: object
      properties:
        name:
          type: string
        canonical_name:
          type: string
        architecture:
          type: string
        languages:
          type: array
          items:
            type: string
        version:
          type: string
        uuid:
          type: string
        batch:
          type: boolean
        streaming:
          type: boolean
        formatted_output:
          type: boolean
      title: ListModelsV1ResponseSttModels
    ErrorResponseLegacyError:
      type: object
      properties:
        err_code:
          type: string
          description: The error code
        err_msg:
          type: string
          description: The error message
        request_id:
          type: string
          description: The request ID
      title: ErrorResponseLegacyError
    AgentThinkModelsV1ResponseModelsItemsOneOf3Id:
      type: string
      enum:
      - openai/gpt-oss-20b
      description: The unique identifier of the Groq model
      title: AgentThinkModelsV1ResponseModelsItemsOneOf3Id
    ErrorResponseTextError:
      type: string
      title: ErrorResponseTextError
    ErrorResponse:
      oneOf:
      - $ref: '#/components/schemas/ErrorResponseTextError'
      - $ref: '#/components/schemas/ErrorResponseLegacyError'
      - $ref: '#/components/schemas/ErrorResponseModernError'
      title: ErrorResponse
    GetModelV1ResponseOneOf1Metadata:
      type: object
      properties:
        accent:
          type: string
        age:
          type: string
        color:
          type: string
        image:
          type: string
          format: uri
        sample:
          type: string
          format: uri
        tags:
          type: array
          items:
            type: string
        use_cases:
          type: array
          items:
            type: string
      title: GetModelV1ResponseOneOf1Metadata
    AgentThinkModelsV1ResponseModelsItems:
      oneOf:
      - $ref: '#/components/schemas/AgentThinkModelsV1ResponseModelsItems0'
      - $ref: '#/components/schemas/AgentThinkModelsV1ResponseModelsItems1'
      - $ref: '#/components/schemas/AgentThinkModelsV1ResponseModelsItems2'
      - $ref: '#/components/schemas/AgentThinkModelsV1ResponseModelsItems3'
      - $ref: '#/components/schemas/AgentThinkModelsV1ResponseModelsItems4'
      title: AgentThinkModelsV1ResponseModelsItems
    ErrorResponseModernError:
      type: object
      properties:
        category:
          type: string
          description: The category of the error
        message:
          type: string
          description: A message about the error
        details:
          type: string
          description: A description of the error
        request_id:
          type: string
          description: The unique identifier of the request
      title: ErrorResponseModernError
    AgentThinkModelsV1ResponseModelsItems2:
      type: object
      properties:
        id:
          $ref: '#/components/schemas/AgentThinkModelsV1ResponseModelsItemsOneOf2Id'
          description: The unique identifier of the Google model
        name:
          type: string
          description: The display name of the model
        provider:
          description: The provider of the model
      required:
      - id
      - name
      - provider
      description: Google models
      title: AgentThinkModelsV1ResponseModelsItems2
    AgentThinkModelsV1ResponseModelsItemsOneOf1Id:
      type: string
      enum:
      - claude-3-5-haiku-latest
      - claude-sonnet-4-20250514
      description: The unique identifier of the Anthropic model
      title: AgentThinkModelsV1ResponseModelsItemsOneOf1Id
    ListModelsV1ResponseTtsModelsMetadata:
      type: object
      properties:
        accent:
          type: string
        age:
          type: string
        color:
          type: string
        image:
          type: string
          format: uri
        sample:
          type: string
          format: uri
        tags:
          type: array
          items:
            type: string
        use_cases:
          type: array
          items:
            type: string
      title: ListModelsV1ResponseTtsModelsMetadata
    AgentThinkModelsV1ResponseModelsItems4:
      type: object
      properties:
        id:
          type: string
          description: The unique identifier of the AWS Bedrock model (any model string accepted for BYO LLMs)
        name:
          type: string
          description: The display name of the model
        provider:
          description: The provider of the model
      required:
      - id
      - name
      - provider
      description: AWS Bedrock models (custom models accepted)
      title: AgentThinkModelsV1ResponseModelsItems4
  securitySchemes:
    ApiKeyAuth:
      type: apiKey
      in: header
      name: Authorization
      description: 'Use `Authorization: Token <API_KEY>`

        Example: `Authorization: Token 12345abcdef`

        '
    JwtAuth:
      type: http
      scheme: bearer
      description: 'Use `Authorization: Bearer <JWT>`

        Example: `Authorization: Bearer eyJhbGciOiJ...`

        '