Creates an embedding vector representing the input text.

POST /embeddings
application/json

Body Required

  • input string | array[string] | array[integer] | array[array] 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. Example Python code for counting tokens. Some models may also impose a limit on total number of tokens summed across inputs.

    One of:

    The string that will be turned into an embedding.

    Default value is empty.

  • model string Required

    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.

    Any of:
  • encoding_format string

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

    Values are float or base64. Default value is float.

  • dimensions integer

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

    Minimum value is 1.

  • user string

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

Responses

  • 200 application/json

    OK

    Hide response attributes Show response attributes object
    • data array[object] Required

      The list of embeddings generated by the model.

      Represents an embedding vector returned by embedding endpoint.

      Hide data attributes Show data attributes object
      • index integer Required

        The index of the embedding in the list of embeddings.

      • embedding array[number] Required

        The embedding vector, which is a list of floats. The length of vector depends on the model as listed in the embedding guide.

      • object string Required

        The object type, which is always "embedding".

        Value is embedding.

    • model string Required

      The name of the model used to generate the embedding.

    • object string Required

      The object type, which is always "list".

      Value is list.

    • usage object Required

      The usage information for the request.

      Hide usage attributes Show usage attributes object
      • prompt_tokens integer Required

        The number of tokens used by the prompt.

      • total_tokens integer Required

        The total number of tokens used by the request.

POST /embeddings
curl \
 --request POST 'https://api.openai.com/v1/embeddings' \
 --header "Authorization: Bearer $ACCESS_TOKEN" \
 --header "Content-Type: application/json" \
 --data '{"input":"This is a test.","model":"text-embedding-3-small","encoding_format":"float","dimensions":42,"user":"user-1234"}'
Request examples
{
  "input": "This is a test.",
  "model": "text-embedding-3-small",
  "encoding_format": "float",
  "dimensions": 42,
  "user": "user-1234"
}
Response examples (200)
{
  "data": [
    {
      "index": 42,
      "embedding": [
        42.0
      ],
      "object": "embedding"
    }
  ],
  "model": "string",
  "object": "list",
  "usage": {
    "prompt_tokens": 42,
    "total_tokens": 42
  }
}