Skip to main content
POST
/
openai
/
v1
/
embeddings
Create embeddings
curl --request POST \
  --url https://api.novita.ai/openai/v1/embeddings \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: <content-type>' \
  --data '
{
  "input": {},
  "model": {},
  "encoding_format": "<string>"
}
'
{
  "object": "<string>",
  "data": [
    {
      "index": 123,
      "embedding": [
        123
      ],
      "object": "<string>"
    }
  ],
  "model": "<string>",
  "usage": {
    "prompt_tokens": 123,
    "total_tokens": 123
  }
}
Creates an embedding vector representing the input text.

ā€‹
Request Headers

ā€‹
Content-Type
string
required
Enum: application/json
ā€‹
Authorization
string
required
Bearer authentication format, for example: Bearer {{API Key}}.

ā€‹
Request Body

ā€‹
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.
ā€‹
model
enum<string>
required
ID of the model to use. Enum: baai/bge-m3.
ā€‹
encoding_format
string
The format to return the embeddings in. Can be either float or base64.

ā€‹
Response

ā€‹
object
string
required
Fixed as list
ā€‹
data
object[]
required
List of embeddings vectors generated by the model.
ā€‹
model
string
required
The ID of the model used.
ā€‹
usage
object
required
Usage information.
Last modified on July 3, 2026