Skip to content
For the complete documentation index, see llms.txt. Markdown versions of documentation pages are available by appending .md to the page URL.
Primary navigation

Suggested
Overview Models Agents Tools Audio & voice Production API reference

Create embeddings

client.embeddings.create(EmbeddingCreateParams { input, model, dimensions, 2 more } body, RequestOptionsoptions?): CreateEmbeddingResponse { data, model, object, usage }
POST/embeddings

Creates an embedding vector representing the input text.

ParametersExpand Collapse
body: EmbeddingCreateParams { input, model, dimensions, 2 more }
input: string | Array<string> | Array<number> | Array<Array<number>>

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 all embedding models), cannot be an empty string, and any array must be 2048 dimensions or less. Example Python code for counting tokens. In addition to the per-input token limit, all embedding models enforce a maximum of 300,000 tokens summed across all inputs in a single request.

model: (string & {}) | EmbeddingModel

ID of the model to use. You can use the List models API to see all of your available models, or see our Model overview for descriptions of them.

dimensions?: number

The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.

minimum1
encoding_format?: "float" | "base64"

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

user?: string

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.

ReturnsExpand Collapse
CreateEmbeddingResponse { data, model, object, usage }
data: Array<Embedding { embedding, index, object } >

The list of embeddings generated by the model.

model: string

The name of the model used to generate the embedding.

object: "list"

The object type, which is always “list”.

usage: Usage { prompt_tokens, total_tokens }

The usage information for the request.

Create embeddings

import OpenAI from "openai";

const openai = new OpenAI();

async function main() {
  const embedding = await openai.embeddings.create({
    model: "text-embedding-3-small",
    input: "Hello world",
    encoding_format: "float",
    dimensions: 3,
  });

  console.log(embedding);
}

main();

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.26726124,
        0.53452248,
        0.80178373
      ],
      "index": 0
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 2,
    "total_tokens": 2
  }
}
Returns Examples
{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "embedding": [
        0.26726124,
        0.53452248,
        0.80178373
      ],
      "index": 0
    }
  ],
  "model": "text-embedding-3-small",
  "usage": {
    "prompt_tokens": 2,
    "total_tokens": 2
  }
}