Create an embed

POST

/v1/embeddings

By obtaining a vector representation of a given input, machine learning models and algorithms can easily use that representation.

Related guide: Embeddings

Create an embedding vector representing the input text.

Request

Header Params

Body Params application/json

Example

{
"model": "text-embedding-3-large",
input: "meow meow meow meow meow meow meow meow meow meow meow"
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location '/v1/embeddings' \
--header 'Authorization: Bearer {{YOUR_API_KEY}}' \
--header 'Content-Type: application/json' \
--data '{
"model": "text-embedding-3-large",
input: "meow meow meow meow meow meow meow meow meow meow meow"
}'

Responses

🟢200Create embeddings

application/json

Bodyapplication/json

Example

{
"object": "list",
"data": [
{
"object": "embedding",
"embedding": [
0.0023064255,
-0.009327292,
.... (1536 floats total for ada-002)
-0.0028842222
],
"index": 0
}
],
"model": "text-embedding-ada-002",
"usage": {
"prompt_tokens": 8,
"total_tokens": 8
}
}

Modified at 2026-09-23 08:28:57

Creation complete

Create chat autocomplete in DeepSeek v3.1 (streaming).