Create Embeddings

User Interface

Dataflow

Field	Description	Comment
Model	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.
Data Type	Select the data to be embedded	String(Default) Array of String
String	Single string input to be embedded
Array of String	Multiple string inputs to be embedded	e.g.)["word1", "word2", "word3"]
Encoding Format	The format to return the embeddings in.	Float (Default) Base64
Dimensions	The number of dimensions the resulting output embeddings should have. (Optional)	Only supported in text-embedding-3 and later models.
User	A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. (Optional)

Response Datas

Key	Description
object	The object type, which is always "embedding".
data[]	Embedding Data
data[].object	Object Type (embedding)
data[].object.embedding[]	Encoding Format (Float or Base64)
data[].object.index	Index of array
model	Model Name
usage	Token Usage Object
usage.prompt_tokens	Number of tokens used in the prompt
usage.total_tokens	Total number of tokens used