Model

text-embedding-3-large

text-embedding-3-large is a high-dimensional text embedding model released by OpenAI. It outputs 3072-dimensional vectors and achieves the strongest embedding quality among the models compared.

Timeline (last 90 days)

Oct 14

OpenAI's text-embedding-3-large returns 3072-dimensional vectors by default, while pgvector's HNSW can index halfvec up to 4000 dimensions.

Unverified50%

Oct 12

text-embedding-3-large嵌入模型为3072维，成本为$0.13/百万token

Unverified50%

All Facts (2)

Unverified

OpenAI's text-embedding-3-large returns 3072-dimensional vectors by default, while pgvector's HNSW can index halfvec up to 4000 dimensions.

50%Unverified

text-embedding-3-large嵌入模型为3072维，成本为$0.13/百万token

50%

Source Articles

Why I Abandoned Answer Generation After Building a RAG Search Engine for 10,000 DocumentsOct 14 Building Production-Grade RAG Systems: Architecture Optimization and MonitoringOct 12