Embedding model

text-embedding-ada-002

Older OpenAI embedding model that represents the meaning of input text as a 1,536-dimensional embedding. It was widely adopted because it replaced several earlier OpenAI embedding models with a single general-purpose model, making embedding workflows simpler and cheaper. It became a common default before the newer text-embedding-3-small and text-embedding-3-large models were introduced. Token IDs on this page use the shared cl100k_base tokenizer vocabulary.