OpenAI: text-embedding-3-large API
OpenAI's most capable and high-performance embedding model. Designed to convert text into high-dimensional numerical vectors, it supports variable output dimensions (up to 3072) and excels in multilingual retrieval (MIRACL) and English tasks (MTEB), serving as a core component for search, clustering, and RAG systems.
- Context window: 8,191 tokens
- Max output: 3,072 tokens
- Input: text
- Output: text
- Released: 2024-01-25
- Knowledge cutoff: 2023-12-31
Frequently Asked Questions
What is the context window of text-embedding-3-large?
text-embedding-3-large supports a context window of up to 8,191 tokens.
What is the knowledge cutoff of text-embedding-3-large?
The knowledge cutoff of text-embedding-3-large is 2023-12-31.