Microsoft

Azure OpenAI Service API

Access to OpenAI's powerful language models through Azure.

GitHub OpenAPI

Documentation

📖
Documentation
https://learn.microsoft.com/en-us/azure/ai-services/openai/
📖
APIReference
https://learn.microsoft.com/en-us/azure/ai-services/openai/reference
📖
Quickstart
https://learn.microsoft.com/en-us/azure/ai-services/openai/quickstart
📖
Authentication
https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/managed-identity

Specifications

⚙
OpenAPI
https://raw.githubusercontent.com/api-evangelist/microsoft/refs/heads/main/openapi/microsoft-azure-openai-openapi.yml

Other Resources

🔗
Pricing
https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/
🔗
NaftikoCapability
https://raw.githubusercontent.com/api-evangelist/microsoft/refs/heads/main/capabilities/azure-openai-audio.yaml
🔗
NaftikoCapability
https://raw.githubusercontent.com/api-evangelist/microsoft/refs/heads/main/capabilities/azure-openai-chat-completions.yaml
🔗
NaftikoCapability
https://raw.githubusercontent.com/api-evangelist/microsoft/refs/heads/main/capabilities/azure-openai-completions.yaml
🔗
NaftikoCapability
https://raw.githubusercontent.com/api-evangelist/microsoft/refs/heads/main/capabilities/azure-openai-embeddings.yaml
🔗
NaftikoCapability
https://raw.githubusercontent.com/api-evangelist/microsoft/refs/heads/main/capabilities/azure-openai-images.yaml

OpenAPI Specification

microsoft-azure-openai-openapi.yml Raw ↑ 
openapi: 3.1.0
info:
  title: Microsoft Azure OpenAI Service API
  description: >-
    Access to OpenAI's powerful language models through Azure including chat
    completions, completions, embeddings, image generation, and audio
    transcription and translation services.
  version: '2024-10-21'
  contact:
    name: Microsoft Azure Support
    url: https://azure.microsoft.com/en-us/support/
  termsOfService: https://www.microsoft.com/en-us/legal/terms-of-use
externalDocs:
  description: Azure OpenAI Service REST API Reference
  url: https://learn.microsoft.com/en-us/azure/ai-services/openai/reference
servers:
  - url: https://{resource-name}.openai.azure.com/openai
    description: Azure OpenAI Service Endpoint
    variables:
      resource-name:
        default: your-resource-name
        description: Your Azure OpenAI resource name
tags:
  - name: Audio
    description: Transcribe and translate audio
  - name: Chat Completions
    description: Create chat completions using conversational models
  - name: Completions
    description: Create text completions
  - name: Embeddings
    description: Create vector embeddings from text
  - name: Images
    description: Generate images from text descriptions
security:
  - apiKey: []
  - oauth2: []
paths:
  /deployments/{deployment-id}/chat/completions:
    post:
      operationId: createChatCompletion
      summary: Microsoft Create chat completion
      description: >-
        Creates a completion for the chat message. Supports function calling,
        tool usage, and streaming responses.
      tags:
        - Chat Completions
      parameters:
        - $ref: '#/components/parameters/deploymentId'
        - $ref: '#/components/parameters/apiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ChatCompletionRequest'
      responses:
        '200':
          description: Chat completion response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ChatCompletionResponse'
        '400':
          description: Invalid request
        '401':
          description: Unauthorized
        '429':
          description: Rate limit exceeded
  /deployments/{deployment-id}/completions:
    post:
      operationId: createCompletion
      summary: Microsoft Create completion
      description: >-
        Creates a completion for the provided prompt and parameters.
      tags:
        - Completions
      parameters:
        - $ref: '#/components/parameters/deploymentId'
        - $ref: '#/components/parameters/apiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CompletionRequest'
      responses:
        '200':
          description: Completion response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CompletionResponse'
        '400':
          description: Invalid request
        '401':
          description: Unauthorized
        '429':
          description: Rate limit exceeded
  /deployments/{deployment-id}/embeddings:
    post:
      operationId: createEmbedding
      summary: Microsoft Create embeddings
      description: >-
        Get a vector representation of a given input that can be consumed by
        machine learning models and algorithms.
      tags:
        - Embeddings
      parameters:
        - $ref: '#/components/parameters/deploymentId'
        - $ref: '#/components/parameters/apiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/EmbeddingRequest'
      responses:
        '200':
          description: Embedding response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EmbeddingResponse'
        '400':
          description: Invalid request
        '401':
          description: Unauthorized
        '429':
          description: Rate limit exceeded
  /deployments/{deployment-id}/images/generations:
    post:
      operationId: createImageGeneration
      summary: Microsoft Generate images
      description: >-
        Creates an image given a prompt using DALL-E models.
      tags:
        - Images
      parameters:
        - $ref: '#/components/parameters/deploymentId'
        - $ref: '#/components/parameters/apiVersion'
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/ImageGenerationRequest'
      responses:
        '200':
          description: Image generation response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ImageGenerationResponse'
        '400':
          description: Invalid request
        '401':
          description: Unauthorized
        '429':
          description: Rate limit exceeded
  /deployments/{deployment-id}/audio/transcriptions:
    post:
      operationId: createTranscription
      summary: Microsoft Transcribe audio
      description: >-
        Transcribes audio into the input language.
      tags:
        - Audio
      parameters:
        - $ref: '#/components/parameters/deploymentId'
        - $ref: '#/components/parameters/apiVersion'
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
                - file
              properties:
                file:
                  type: string
                  format: binary
                  description: The audio file to transcribe
                language:
                  type: string
                  description: Language of the input audio in ISO-639-1 format
                prompt:
                  type: string
                  description: Optional text to guide the model's style
                response_format:
                  type: string
                  enum:
                    - json
                    - text
                    - srt
                    - verbose_json
                    - vtt
                  default: json
                temperature:
                  type: number
                  minimum: 0
                  maximum: 1
      responses:
        '200':
          description: Transcription response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TranscriptionResponse'
        '400':
          description: Invalid request
        '401':
          description: Unauthorized
  /deployments/{deployment-id}/audio/translations:
    post:
      operationId: createTranslation
      summary: Microsoft Translate audio
      description: >-
        Transcribes and translates input audio into English text.
      tags:
        - Audio
      parameters:
        - $ref: '#/components/parameters/deploymentId'
        - $ref: '#/components/parameters/apiVersion'
      requestBody:
        required: true
        content:
          multipart/form-data:
            schema:
              type: object
              required:
                - file
              properties:
                file:
                  type: string
                  format: binary
                  description: The audio file to translate
                prompt:
                  type: string
                response_format:
                  type: string
                  enum:
                    - json
                    - text
                    - srt
                    - verbose_json
                    - vtt
                  default: json
                temperature:
                  type: number
                  minimum: 0
                  maximum: 1
      responses:
        '200':
          description: Translation response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TranscriptionResponse'
        '400':
          description: Invalid request
        '401':
          description: Unauthorized
components:
  securitySchemes:
    apiKey:
      type: apiKey
      name: api-key
      in: header
      description: Azure OpenAI API key
    oauth2:
      type: oauth2
      description: Microsoft Entra ID OAuth 2.0
      flows:
        clientCredentials:
          tokenUrl: https://login.microsoftonline.com/{tenantId}/oauth2/v2.0/token
          scopes:
            https://cognitiveservices.azure.com/.default: Access Azure OpenAI
  parameters:
    deploymentId:
      name: deployment-id
      in: path
      required: true
      description: The deployment name for the model
      schema:
        type: string
    apiVersion:
      name: api-version
      in: query
      required: true
      description: The API version to use
      schema:
        type: string
        default: '2024-10-21'
  schemas:
    ChatCompletionRequest:
      type: object
      required:
        - messages
      properties:
        messages:
          type: array
          items:
            type: object
            required:
              - role
              - content
            properties:
              role:
                type: string
                enum:
                  - system
                  - user
                  - assistant
                  - tool
              content:
                type: string
              name:
                type: string
          description: A list of messages comprising the conversation
        temperature:
          type: number
          minimum: 0
          maximum: 2
          default: 1
          description: Sampling temperature
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
          description: Nucleus sampling parameter
        max_tokens:
          type: integer
          description: Maximum number of tokens to generate
        stream:
          type: boolean
          default: false
          description: Whether to stream partial message deltas
        stop:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
          description: Sequences where the API will stop generating
        presence_penalty:
          type: number
          minimum: -2
          maximum: 2
          default: 0
        frequency_penalty:
          type: number
          minimum: -2
          maximum: 2
          default: 0
        tools:
          type: array
          items:
            type: object
            properties:
              type:
                type: string
                enum:
                  - function
              function:
                type: object
                properties:
                  name:
                    type: string
                  description:
                    type: string
                  parameters:
                    type: object
          description: A list of tools the model may call
        response_format:
          type: object
          properties:
            type:
              type: string
              enum:
                - text
                - json_object
    ChatCompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
          enum:
            - chat.completion
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              index:
                type: integer
              message:
                type: object
                properties:
                  role:
                    type: string
                  content:
                    type: string
              finish_reason:
                type: string
                enum:
                  - stop
                  - length
                  - content_filter
                  - tool_calls
        usage:
          $ref: '#/components/schemas/Usage'
    CompletionRequest:
      type: object
      required:
        - prompt
      properties:
        prompt:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
          description: The prompt(s) to generate completions for
        max_tokens:
          type: integer
          default: 16
        temperature:
          type: number
          minimum: 0
          maximum: 2
          default: 1
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
        n:
          type: integer
          minimum: 1
          default: 1
          description: Number of completions to generate
        stream:
          type: boolean
          default: false
        stop:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
        presence_penalty:
          type: number
          minimum: -2
          maximum: 2
          default: 0
        frequency_penalty:
          type: number
          minimum: -2
          maximum: 2
          default: 0
    CompletionResponse:
      type: object
      properties:
        id:
          type: string
        object:
          type: string
        created:
          type: integer
        model:
          type: string
        choices:
          type: array
          items:
            type: object
            properties:
              text:
                type: string
              index:
                type: integer
              finish_reason:
                type: string
        usage:
          $ref: '#/components/schemas/Usage'
    EmbeddingRequest:
      type: object
      required:
        - input
      properties:
        input:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
          description: Input text to embed
        encoding_format:
          type: string
          enum:
            - float
            - base64
          default: float
    EmbeddingResponse:
      type: object
      properties:
        object:
          type: string
          enum:
            - list
        data:
          type: array
          items:
            type: object
            properties:
              object:
                type: string
                enum:
                  - embedding
              embedding:
                type: array
                items:
                  type: number
              index:
                type: integer
        model:
          type: string
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
            total_tokens:
              type: integer
    ImageGenerationRequest:
      type: object
      required:
        - prompt
      properties:
        prompt:
          type: string
          description: A text description of the desired image
        n:
          type: integer
          minimum: 1
          maximum: 10
          default: 1
          description: Number of images to generate
        size:
          type: string
          enum:
            - 256x256
            - 512x512
            - 1024x1024
            - 1792x1024
            - 1024x1792
          default: 1024x1024
        quality:
          type: string
          enum:
            - standard
            - hd
          default: standard
        style:
          type: string
          enum:
            - natural
            - vivid
          default: vivid
        response_format:
          type: string
          enum:
            - url
            - b64_json
          default: url
    ImageGenerationResponse:
      type: object
      properties:
        created:
          type: integer
        data:
          type: array
          items:
            type: object
            properties:
              url:
                type: string
              b64_json:
                type: string
              revised_prompt:
                type: string
    TranscriptionResponse:
      type: object
      properties:
        text:
          type: string
          description: The transcribed or translated text
        task:
          type: string
        language:
          type: string
        duration:
          type: number
    Usage:
      type: object
      properties:
        prompt_tokens:
          type: integer
        completion_tokens:
          type: integer
        total_tokens:
          type: integer