Create Embeddings

POST

/v1/embeddings

• Returns vector representations for the given input for use by ML models and algorithms
• Creates embedding vectors that represent input text
• input accepts a string or token array; pass an array of strings in one request for batch embeddings
• Official docs: Embeddings

Authorizations

bearer

Type

HTTP (bearer)

Request Body

application/json

object

ID of the model to use. Use the List models API to see available models, or see the model overview for descriptions.

Input text to embed, encoded as a string or token array. To get embeddings for multiple inputs in a single request, pass an array of strings or an array of token arrays. Each input must not exceed 8192 tokens in length.

Responses

Content-Type

application/json

object

object[]

Required

object

Required