TextEmbeddingAda3Large

text-embedding-3-large is currently the most capable embedding model for both english and non-english tasks.

Currently provides best embedding quality; supports multiple dimensions for flexibility and cost tradeoff.

Outputs: 3072-dimensional vectors (or 256-/512-/1024-dimensional vectors, optionally) Max input tokens: 8191 Released: Jan 2024

Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.

See also