A4F

Documentation

API Reference
POST

Embeddings

/v1/embeddings

Get a vector representation of a given input that can be easily consumed by machine learning models and algorithms.

Interactive Example

Request & Response Example

curl https://api.a4f.co/v1/embeddings \
  -H "Authorization: Bearer YOUR_A4F_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "provider-2/text-embedding-3-small",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Headers

Authorization

string
Required
Bearer token for authentication. Your A4F API key.

Request Body

model

string
Required
ID of the embedding model to use. Must be a model of type embeddings.

input

string or array of strings
Required
The input text or texts to embed.

encoding_format

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

Default: float

dimensions

integer
The number of dimensions the resulting output embeddings should have. Only supported by certain models. Requesting an unsupported dimension will result in an error.

user

string
A unique identifier representing your end-user, for monitoring and abuse detection.

Response Body (200 OK)

object

string
The object type, which is always 'list'.

data

array of objects
A list of embedding objects.

object

string
The object type, which is always 'embedding'.

embedding

array of numbers or string
The embedding vector, which is a list of floats or a base64 encoded string.

index

integer
The index of the embedding in the list.

model

string
The model ID used for the embedding.

usage

object
Usage statistics for the request.

prompt_tokens

integer
The number of tokens in the input.

total_tokens

integer
The total number of tokens consumed by the request.

Was this page helpful?

Image Edits
API reference for editing images with text prompts.
Previous
Audio Speech (TTS)
API reference for text-to-speech audio generation.
Next