OpenAI Embeddings API

openapi: 3.1.0
info:
  title: OpenAI APIs OpenAI Embeddings API
  description: >-
    API for converting text into numerical vector representations. Embeddings
    measure the relatedness of text strings and are useful for search,
    clustering, recommendations, and anomaly detection.
  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 Embeddings API Documentation
  url: https://platform.openai.com/docs/api-reference/embeddings
servers:
  - url: https://api.openai.com/v1
    description: OpenAI Production API
tags:
  - name: Embeddings
    description: Text embedding operations
security:
  - bearerAuth: []
paths:
  /embeddings:
    post:
      operationId: createEmbedding
      summary: OpenAI APIs Create embeddings
      description: >-
        Creates an embedding vector representing the input text. The resulting
        vector can be used for semantic search, clustering, and other tasks.
      tags:
        - Embeddings
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateEmbeddingRequest'
      responses:
        '200':
          description: Embedding response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/EmbeddingResponse'
        '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:
    CreateEmbeddingRequest:
      type: object
      required:
        - model
        - input
      properties:
        input:
          oneOf:
            - type: string
            - type: array
              items:
                type: string
            - type: array
              items:
                type: integer
            - type: array
              items:
                type: array
                items:
                  type: integer
          description: Input text to embed, as a string or array of strings/tokens
        model:
          type: string
          description: ID of the model to use (e.g., text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large)
          examples:
            - text-embedding-3-small
        encoding_format:
          type: string
          enum:
            - float
            - base64
          default: float
          description: The format to return the embeddings in
        dimensions:
          type: integer
          description: >-
            The number of dimensions the resulting output embeddings should
            have. Supported in text-embedding-3 and later models.
        user:
          type: string
          description: A unique identifier representing your end-user
    EmbeddingResponse:
      type: object
      properties:
        object:
          type: string
          enum:
            - list
        data:
          type: array
          items:
            $ref: '#/components/schemas/Embedding'
        model:
          type: string
          description: The model used for embedding
        usage:
          type: object
          properties:
            prompt_tokens:
              type: integer
              description: Number of tokens in the input
            total_tokens:
              type: integer
              description: Total number of tokens used
    Embedding:
      type: object
      properties:
        object:
          type: string
          enum:
            - embedding
        embedding:
          oneOf:
            - type: array
              items:
                type: number
            - type: string
          description: The embedding vector (float array or base64)
        index:
          type: integer
          description: The index of the embedding in the list of embeddings