OpenAI: text-embedding-3-small API
OpenAI's highly cost-effective 3rd-generation embedding model. As the successor to ada-002, it offers significant improvements in multilingual and English retrieval tasks. It utilizes Matryoshka Representation Learning (MRL), allowing for flexible dimension reduction with minimal impact on accuracy.
- Context window: 8,191 tokens
- Max output: 1,536 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-small?
text-embedding-3-small supports a context window of up to 8,191 tokens.
What is the knowledge cutoff of text-embedding-3-small?
The knowledge cutoff of text-embedding-3-small is 2023-12-31.