Embedding model

text-embedding-3-small

Small third-generation OpenAI embedding model optimized for efficient search, clustering, classification, and recommendations. Token IDs on this page use the shared cl100k_base tokenizer vocabulary.

OpenAI

Endpoint

Embeddings

Status

Current

Default dimensions

1,536

Max input

8,192 tokens

Tokenizer

cl100k_base

Tokenizer tokens

100,261 known tokens (100,256 mergeable)

Open model token IDs Open tokenizer reference OpenAI model docs