OpenAI text-embedding-3-large
used in
0
stacks
OpenAI's most capable embedding model for English and non-English retrieval, served via usage-priced API.
text-embedding-3-large is described by OpenAI as its most capable embedding model for both English and non-English tasks, producing numerical text representations for search, clustering, recommendations, anomaly detection, and classification. It is API-only with per-token usage pricing; text-embedding-3-small is offered as a lower-cost, less capable alternative.
Strengths
- Strong general-purpose retrieval quality across English and non-English text
- Ubiquitous ecosystem support in vector databases and RAG frameworks
- Simple usage-based pricing with a cheaper small variant for cost-sensitive paths
Tradeoffs
- API-only (no open weights or on-prem option)
- General-purpose model with no domain-specialized variants, unlike some competitors