Microsoft Azure Key Phrases API

The keyPhrases API from Microsoft Azure — 1 operation(s) for keyphrases.

Documentation GitHub OpenAPI

Operations 1

Each operation below carries the questions people ask an LLM about it and the instructions they give an agent to run it. Generated by API Evangelist overlay

POST /keyPhrases Extract key phrases from text · Microsoft Azure Key Phrases #

Ask an LLM

“How do I pull the main talking points out of a block of text?”

“Can I get statistics along with extracted key phrases?”

Tell an agent

Extract key phrases from {input}.

Find key phrases in {input} using model version {version} and include stats.

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/microsoft-azure:microsoft-azure-keyphrases-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

openapi: 3.2.0
info:
  version: v3.1-preview.4
  contact:
    name: Microsoft Cognitive Services
    url: https://azure.microsoft.com/en-us/services/cognitive-services/text-analytics/
    email: mlapi@microsoft.com
  title: Microsoft Azure Text Analytics Client Key Phrases API
  description: The Text Analytics API is a suite of natural language processing (NLP) services built with best-in-class Microsoft machine learning algorithms. The API can be used to analyze unstructured text for tasks such as sentiment analysis, key phrase extraction and language detection. Functionality for analysis of text specific to the healthcare domain and personal information are also available in the API. Further documentation can be found in https://docs.microsoft.com/en-us/azure/cognitive-services/text-analytics/overview
security:
- apim_key: []
tags:
- name: keyPhrases
paths:
  /keyPhrases:
    post:
      summary: Microsoft Azure Key Phrases
      description: The API returns a list of strings denoting the key phrases in the input text. See the Supported languages in Text Analytics API for the list of enabled languages.
      operationId: microsoftAzureKeyphrases
      parameters:
      - $ref: '#/components/parameters/ModelVersion'
      - $ref: '#/components/parameters/ShowStats'
      - $ref: '#/components/parameters/MultiLanguageInput'
      responses:
        '200':
          description: A successful response results in 0 or more key phrases identified in each valid document
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/KeyPhraseResult'
            text/json:
              schema:
                $ref: '#/components/schemas/KeyPhraseResult'
        '400':
          description: Bad Request.
          x-ms-error-response: true
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
            text/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
        '500':
          description: Internal error response
          x-ms-error-response: true
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
            text/json:
              schema:
                $ref: '#/components/schemas/ErrorResponse'
      x-ms-examples:
        Successful Key Phrase request:
          $ref: .//examples//SuccessfulKeyPhrasesRequest.json
      deprecated: false
      tags:
      - keyPhrases
components:
  parameters:
    ModelVersion:
      name: model-version
      in: query
      description: '(Optional) This value indicates which model will be used for scoring. If a model-version is not specified, the API should default to the latest, non-preview version. '
      required: false
      x-ms-parameter-location: method
      schema:
        type: string
    MultiLanguageInput:
      in: body
      name: input
      description: Collection of documents to analyze.
      required: true
      schema:
        $ref: '#/components/schemas/MultiLanguageBatchInput'
      x-ms-parameter-location: method
    ShowStats:
      name: showStats
      in: query
      description: (Optional) if set to true, response will contain request and document level statistics.
      required: false
      x-ms-parameter-location: method
      schema:
        type: boolean
  schemas:
    RequestStatistics:
      type: object
      required:
      - documentsCount
      - validDocumentsCount
      - erroneousDocumentsCount
      - transactionsCount
      properties:
        documentsCount:
          type: integer
          format: int32
          description: Number of documents submitted in the request.
        validDocumentsCount:
          type: integer
          format: int32
          description: Number of valid documents. This excludes empty, over-size limit or non-supported languages documents.
        erroneousDocumentsCount:
          type: integer
          format: int32
          description: Number of invalid documents. This includes empty, over-size limit or non-supported languages documents.
        transactionsCount:
          type: integer
          format: int64
          description: Number of transactions for the request.
      description: if showStats=true was specified in the request this field will contain information about the request payload.
    InnerError:
      type: object
      required:
      - code
      - message
      properties:
        code:
          type: string
          enum:
          - InvalidParameterValue
          - InvalidRequestBodyFormat
          - EmptyRequest
          - MissingInputRecords
          - InvalidDocument
          - ModelVersionIncorrect
          - InvalidDocumentBatch
          - UnsupportedLanguageCode
          - InvalidCountryHint
          x-ms-enum:
            name: InnerErrorCodeValue
            modelAsString: true
          description: Error code.
        message:
          type: string
          description: Error message.
        details:
          type: object
          additionalProperties:
            type: string
          description: Error details.
        target:
          type: string
          description: Error target.
        innererror:
          $ref: '#/components/schemas/InnerError'
          description: Inner error contains more specific information.
    MultiLanguageInput:
      type: object
      required:
      - id
      - text
      properties:
        id:
          type: string
          description: A unique, non-empty document identifier.
        text:
          type: string
          description: The input text to process.
        language:
          type: string
          description: (Optional) This is the 2 letter ISO 639-1 representation of a language. For example, use "en" for English; "es" for Spanish etc. If not set, use "en" for English as default.
      description: Contains an input document to be analyzed by the service.
    ErrorResponse:
      type: object
      required:
      - error
      properties:
        error:
          type: object
          description: Document Error.
          $ref: '#/components/schemas/TextAnalyticsError'
    DocumentKeyPhrases:
      type: object
      required:
      - id
      - keyPhrases
      - warnings
      properties:
        id:
          type: string
          description: Unique, non-empty document identifier.
        keyPhrases:
          type: array
          description: A list of representative words or phrases. The number of key phrases returned is proportional to the number of words in the input document.
          items:
            type: string
        warnings:
          type: array
          description: Warnings encountered while processing document.
          items:
            $ref: '#/components/schemas/TextAnalyticsWarning'
        statistics:
          description: if showStats=true was specified in the request this field will contain information about the document payload.
          $ref: '#/components/schemas/DocumentStatistics'
    TextAnalyticsWarning:
      type: object
      required:
      - code
      - message
      properties:
        code:
          type: string
          enum:
          - LongWordsInDocument
          - DocumentTruncated
          x-ms-enum:
            name: WarningCodeValue
            modelAsString: true
          description: Error code.
        message:
          type: string
          description: Warning message.
        targetRef:
          type: string
          description: A JSON pointer reference indicating the target object.
    TextAnalyticsError:
      type: object
      required:
      - code
      - message
      properties:
        code:
          type: string
          enum:
          - InvalidRequest
          - InvalidArgument
          - InternalServerError
          - ServiceUnavailable
          - NotFound
          x-ms-enum:
            name: ErrorCodeValue
            modelAsString: false
          description: Error code.
        message:
          type: string
          description: Error message.
        target:
          type: string
          description: Error target.
        innererror:
          $ref: '#/components/schemas/InnerError'
          description: Inner error contains more specific information.
        details:
          type: array
          description: Details about specific errors that led to this reported error.
          items:
            $ref: '#/components/schemas/TextAnalyticsError'
    MultiLanguageBatchInput:
      type: object
      required:
      - documents
      properties:
        documents:
          type: array
          description: The set of documents to process as part of this batch.
          items:
            $ref: '#/components/schemas/MultiLanguageInput'
      description: Contains a set of input documents to be analyzed by the service.
    DocumentStatistics:
      type: object
      required:
      - charactersCount
      - transactionsCount
      properties:
        charactersCount:
          type: integer
          format: int32
          description: Number of text elements recognized in the document.
        transactionsCount:
          type: integer
          format: int32
          description: Number of transactions for the document.
      description: if showStats=true was specified in the request this field will contain information about the document payload.
    DocumentError:
      type: object
      required:
      - id
      - error
      properties:
        id:
          type: string
          description: Document Id.
        error:
          type: object
          description: Document Error.
          $ref: '#/components/schemas/TextAnalyticsError'
    KeyPhraseResult:
      type: object
      required:
      - documents
      - errors
      - modelVersion
      properties:
        documents:
          type: array
          description: Response by document
          items:
            $ref: '#/components/schemas/DocumentKeyPhrases'
        errors:
          type: array
          description: Errors by document id.
          items:
            $ref: '#/components/schemas/DocumentError'
        statistics:
          $ref: '#/components/schemas/RequestStatistics'
        modelVersion:
          type: string
          description: This field indicates which model is used for scoring.
  securitySchemes:
    apim_key:
      type: apiKey
      name: Ocp-Apim-Subscription-Key
      in: header
x-ms-parameterized-host:
  hostTemplate: '{Endpoint}/text/analytics/v3.1-preview.4'
  useSchemePrefix: false
  parameters:
  - $ref: '#/components/parameters/Endpoint'