Sign in

v1

latestOpenAPI 3.1.02026-07-267724480.0 KB

Create Embeddings

post/v1/embeddings

Request body

modelstring required

The embedding model to use. See the Models page for current embedding model IDs.

encoding_format'float' | 'base64'

The format of the returned embedding vectors. float returns an array of floating-point numbers. base64 returns a base64-encoded string representation, which can reduce response size for large batches.

dimensionsinteger

The number of dimensions for the output embedding vector. Only supported by text-embedding-3-* models. Reducing dimensions can lower storage costs while maintaining most of the embedding's utility.

userstring

A unique identifier for your end-user, which can help monitor and detect abuse.

Example request

{
  "model": "text-embedding-3-small"
}

Response

A list of embedding vectors for the input text(s).

object'list'

The object type, always list.

modelstring

The model used to generate the embeddings.

Example response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        -0.0021,
        -0.0491,
        0.0209,
        0.0314,
        -0.0453
      ]
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 2,
    "total_tokens": 2
  }
}