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

# Create embeddings

Creates an embedding vector representing the input text.

## Request Headers

**Content-Type** `string` *required*

Enum: `application/json`

**Authorization** `string` *required*

Bearer authentication format, for example: Bearer \{\{API Key}}.

## Request Body

**input** `string | arrary` *required*

Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. The input must not exceed the max input tokens for the model (8192 tokens for text-embedding-ada-002), cannot be an empty string, and any array must be 2048 dimensions or less.

**model** `enum\<string\>` *required*

ID of the model to use. Enum: `baai/bge-m3`.

**encoding\_format** `string`

The format to return the embeddings in. Can be either float or base64.

## Response

**object** `string` *required*

Fixed as list

**data** `object[]` *required*

List of embeddings vectors generated by the model.

**properties**

**index** `integer` *required*

The index of the embedding vector.

**embedding** `number[]` *required*

The embedding vector.

**object** `string` *required*

Fixed as embedding

**model** `string` *required*

The ID of the model used.

**usage** `object` *required*

Usage information.

**properties**

**prompt\_tokens** `integer` *required*

The number of prompt tokens.

**total\_tokens** `integer` *required*

The number of total tokens.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.