go/resources/embeddings/methods/create/index.md 2026-07-10 23:02 UTC to 2026-07-12 06:58 UTC

Create embeddings

client.Embeddings.New(ctx, body) (*CreateEmbeddingResponse, error)

post /embeddings

Creates an embedding vector representing the input text.

Parameters

• body EmbeddingNewParams

  • Input param.Field[EmbeddingNewParamsInputUnion]

    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.

    • string

    • type EmbeddingNewParamsInputArrayOfStrings []string

      The array of strings that will be turned into an embedding.

    • type EmbeddingNewParamsInputArrayOfTokens []int64

      The array of integers that will be turned into an embedding.

    • type EmbeddingNewParamsInputArrayOfTokenArrays [][]int64

      The array of arrays containing integers that will be turned into an embedding.

  • Model param.Field[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.

    • string

    • type EmbeddingModel string

      • const EmbeddingModelTextEmbeddingAda002 EmbeddingModel = "text-embedding-ada-002"

      • const EmbeddingModelTextEmbedding3Small EmbeddingModel = "text-embedding-3-small"

      • const EmbeddingModelTextEmbedding3Large EmbeddingModel = "text-embedding-3-large"

  • Dimensions param.Field[int64]

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

  • EncodingFormat param.Field[EmbeddingNewParamsEncodingFormat]

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

    • const EmbeddingNewParamsEncodingFormatFloat EmbeddingNewParamsEncodingFormat = "float"

    • const EmbeddingNewParamsEncodingFormatBase64 EmbeddingNewParamsEncodingFormat = "base64"

  • User param.Field[string]

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

Returns

• type CreateEmbeddingResponse struct{…}

  • Data []Embedding

    The list of embeddings generated by the model.

    • Embedding []float64

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

    • Index int64

      The index of the embedding in the list of embeddings.

    • Object Embedding

      The object type, which is always "embedding".

      • const EmbeddingEmbedding Embedding = "embedding"

  • Model string

    The name of the model used to generate the embedding.

  • Object List

    The object type, which is always "list".

    • const ListList List = "list"

  • Usage CreateEmbeddingResponseUsage

    The usage information for the request.

    • PromptTokens int64

      The number of tokens used by the prompt.

    • TotalTokens int64

      The total number of tokens used by the request.

Example

package main

import (
  "context"
  "fmt"

  "github.com/openai/openai-go"
  "github.com/openai/openai-go/option"
)

func main() {
  client := openai.NewClient(
    option.WithAPIKey("My API Key"),
  )
  createEmbeddingResponse, err := client.Embeddings.New(context.TODO(), openai.EmbeddingNewParams{
    Input: openai.EmbeddingNewParamsInputUnion{
      OfString: openai.String("The quick brown fox jumped over the lazy dog"),
    },
    Model: openai.EmbeddingModelTextEmbedding3Small,
  })
  if err != nil {
    panic(err.Error())
  }
  fmt.Printf("%+v\n", createEmbeddingResponse.Data)
}

Response

{
  "data": [
    {
      "embedding": [
        0
      ],
      "index": 0,
      "object": "embedding"
    }
  ],
  "model": "model",
  "object": "list",
  "usage": {
    "prompt_tokens": 0,
    "total_tokens": 0
  }
}