Text Embedding 3 Large

Higher-fidelity embeddings when retrieval quality matters.

Vendor: OpenAI
Released: May 2026
Model id: text-embedding-3-large

The larger OpenAI embedding model produces richer vectors (better recall on subtle or crowded corpora) at a higher per-token cost than the small model.

Best for: retrieval quality over cost.

Run Text Embedding 3 Large in a workspace

Pick it per workspace from the model settings and switch any time. Inference is included in the plan, or bring a key of the team's own.