OpenAI Completions API

openapi: 3.1.0
info:
  title: OpenAI APIs OpenAI Completions API
  description: >-
    Legacy text completion API for generating text continuations using GPT
    models. Given a prompt, the model returns one or more predicted
    completions along with token probabilities.
  version: '1.0'
  contact:
    name: OpenAI Support
    email: [email protected]
    url: https://help.openai.com
  termsOfService: https://openai.com/policies/terms-of-use
externalDocs:
  description: OpenAI Completions API Documentation
  url: https://platform.openai.com/docs/api-reference/completions
servers:
  - url: https://api.openai.com/v1
    description: OpenAI Production API
tags:
  - name: Completions
    description: Legacy text completion operations
security:
  - bearerAuth: []
paths:
  /completions:
    post:
      operationId: createCompletion
      summary: OpenAI APIs Create completion
      description: >-
        Creates a completion for the provided prompt and parameters. This is
        a legacy endpoint; use the Chat Completions API for new applications.
      tags:
        - Completions
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateCompletionRequest'
      responses:
        '200':
          description: Completion response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CompletionResponse'
        '400':
          description: Invalid request
        '401':
          description: Unauthorized - invalid or missing API key
        '429':
          description: Rate limit exceeded
        '500':
          description: Server error
components:
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      bearerFormat: API Key
      description: OpenAI API key passed as a Bearer token
  schemas:
    CreateCompletionRequest:
      type: object
      required:
        - model
        - prompt
      properties:
        model:
          type: string
          description: ID of the model to use (e.g., gpt-3.5-turbo-instruct)
          examples:
            - gpt-3.5-turbo-instruct
        prompt:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
          description: The prompt(s) to generate completions for
        suffix:
          type: string
          description: The suffix that comes after a completion of inserted text
        max_tokens:
          type: integer
          default: 16
          description: Maximum number of tokens to generate in the completion
        temperature:
          type: number
          minimum: 0
          maximum: 2
          default: 1
          description: Sampling temperature between 0 and 2
        top_p:
          type: number
          minimum: 0
          maximum: 1
          default: 1
          description: Nucleus sampling parameter
        n:
          type: integer
          minimum: 1
          default: 1
          description: Number of completions to generate for each prompt
        stream:
          type: boolean
          default: false
          description: Whether to stream back partial progress
        logprobs:
          type: integer
          minimum: 0
          maximum: 5
          description: Include log probabilities on the most likely output tokens
        echo:
          type: boolean
          default: false
          description: Echo back the prompt in addition to the completion
        stop:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
          description: Up to 4 sequences where the API will stop generating
        presence_penalty:
          type: number
          minimum: -2
          maximum: 2
          default: 0
          description: Penalize new tokens based on presence in text so far
        frequency_penalty:
          type: number
          minimum: -2
          maximum: 2
          default: 0
          description: Penalize new tokens based on frequency in text so far
        best_of:
          type: integer
          minimum: 1
          default: 1
          description: Generates best_of completions and returns the best
        logit_bias:
          type: object
          additionalProperties:
            type: number
          description: Modify the likelihood of specified tokens appearing
        user:
          type: string
          description: A unique identifier representing your end-user
    CompletionResponse:
      type: object
      properties:
        id:
          type: string
          description: A unique identifier for the completion
        object:
          type: string
          enum:
            - text_completion
        created:
          type: integer
          description: Unix timestamp of when the completion was created
        model:
          type: string
          description: The model used for the completion
        choices:
          type: array
          items:
            type: object
            properties:
              text:
                type: string
                description: The generated text
              index:
                type: integer
              logprobs:
                type: object
                nullable: true
              finish_reason:
                type: string
                enum:
                  - stop
                  - length
        usage:
          $ref: '#/components/schemas/Usage'
        system_fingerprint:
          type: string
          description: Fingerprint of the backend configuration
    Usage:
      type: object
      properties:
        prompt_tokens:
          type: integer
          description: Number of tokens in the prompt
        completion_tokens:
          type: integer
          description: Number of tokens in the generated completion
        total_tokens:
          type: integer
          description: Total number of tokens used