openapi: 3.1.0
info:
  title: Microsoft Azure Cognitive Services Accounts Chat Completions API
  description: APIs for vision, speech, language, and decision-making AI capabilities including Computer Vision, Text Analytics, and Translator services.
  version: '3.2'
  contact:
    name: Microsoft Azure Support
    url: https://azure.microsoft.com/en-us/support/
  termsOfService: https://www.microsoft.com/en-us/legal/terms-of-use
servers:
- url: https://{region}.api.cognitive.microsoft.com
  description: Azure Cognitive Services Regional Endpoint
  variables:
    region:
      default: eastus
      description: Azure region for the Cognitive Services resource
security:
- apiKey: []
tags:
- name: Chat Completions
  description: Create chat completions using conversational models
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
components:
  schemas:
    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'
    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
    Usage:
      type: object
      properties:
        prompt_tokens:
          type: integer
        completion_tokens:
          type: integer
        total_tokens:
          type: integer
  parameters:
    apiVersion:
      name: api-version
      in: query
      required: true
      description: The API version to use
      schema:
        type: string
        default: '2024-10-21'
    deploymentId:
      name: deployment-id
      in: path
      required: true
      description: The deployment name for the model
      schema:
        type: string
  securitySchemes:
    apiKey:
      type: apiKey
      name: Ocp-Apim-Subscription-Key
      in: header
      description: Azure Cognitive Services subscription key
externalDocs:
  description: Azure AI Services Documentation
  url: https://learn.microsoft.com/en-us/azure/ai-services/