> ## Documentation Index
> Fetch the complete documentation index at: https://urantia.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Get Embedding

> Returns the embedding vector for a single paragraph.

Use `?model=large` (default) for the 3072-dimensional `text-embedding-3-large` vector — the canonical embedding used by the cross-references feature. Use `?model=small` for the 1536-dimensional `text-embedding-3-small` vector that powers `/search/semantic`.

The response includes `model` and `dimensions` fields so consumers can detect mismatches if they store vectors locally and compare against new responses. The `X-Embedding-Model` response header carries the same signal for byte-streaming clients.



## OpenAPI

````yaml GET /embeddings/{ref}
openapi: 3.1.0
info:
  title: Urantia Papers API
  version: 1.0.0
  description: >-
    A developer and AI-agent friendly API for the Urantia Papers. Provides
    full-text search, structured content access, and audio URLs for all 17,000+
    paragraphs across 197 papers.
servers:
  - url: https://api.urantia.dev
    description: Production
  - url: http://localhost:3000
    description: Local development
security: []
paths:
  /embeddings/{ref}:
    get:
      tags:
        - Embeddings
      summary: Get the embedding vector for a paragraph
      description: >-
        Returns the embedding vector for a single paragraph.


        Use `?model=large` (default) for the 3072-dimensional
        `text-embedding-3-large` vector — the canonical embedding used by the
        cross-references feature. Use `?model=small` for the 1536-dimensional
        `text-embedding-3-small` vector that powers `/search/semantic`.


        The response includes `model` and `dimensions` fields so consumers can
        detect mismatches if they store vectors locally and compare against new
        responses. The `X-Embedding-Model` response header carries the same
        signal for byte-streaming clients.
      operationId: getEmbedding
      parameters:
        - schema:
            type: string
          required: true
          name: ref
          in: path
        - schema:
            type: string
            enum:
              - small
              - large
            default: large
          required: false
          name: model
          in: query
      responses:
        '200':
          description: Embedding vector
          content:
            application/json:
              schema:
                type: object
                properties:
                  data:
                    type: object
                    properties:
                      standardReferenceId:
                        type: string
                      model:
                        type: string
                      dimensions:
                        type: integer
                      embedding:
                        type: array
                        items:
                          type: number
                    required:
                      - standardReferenceId
                      - model
                      - dimensions
                      - embedding
                required:
                  - data
        '404':
          description: Paragraph or embedding not found
          content:
            application/json:
              schema:
                type: object
                properties:
                  type:
                    type: string
                  title:
                    type: string
                  status:
                    type: integer
                  detail:
                    type: string
                required:
                  - type
                  - title
                  - status
                  - detail

````