OpenAI Confirms text-embedding-3-small Is Not Deprecated Following Communication Mistake
GPT
LLM
AI Economics
RAG
OpenAI confirmed that
text-embedding-3-small is not being deprecated, reversing a previous notice that suggested the model would be retired. Romain Huet, Head of Developer Experience, clarified that the communication was a mistake. This model is a primary tool for generating embeddings (numerical representations of text used for semantic search).The update follows a period of model pruning, including when OpenAI retired early GPT-5 models from its interface. Unlike chat models, retiring an embedding model forces developers to re-index their entire knowledge base. This clarification provides critical stability for teams building Retrieval-Augmented Generation (RAG) systems (grounding AI in external data).
You do not need to migrate vector stores or change API configurations for text-embedding-3-small. OpenAI will email users to formally clarify the model's status and is investigating where the incorrect information originated. The model remains available for all projects via standard API endpoints.
Frequently asked questions
- Is OpenAI deprecating the text-embedding-3-small model?
- No, OpenAI has confirmed that text-embedding-3-small is not being deprecated. The company clarified that any previous information suggesting the model would be retired was a mistake. Developers can continue using the model for their applications and vector databases without worrying about a shutdown or forced migration to a different embedding version.
- What should I do if I received an email about text-embedding-3-small retiring?
- If you received a notice regarding the deprecation of this model, you can safely ignore the retirement date. OpenAI is currently investigating the source of the incorrect communication and plans to send a follow-up email to all affected users to clarify the situation. No action is required to maintain your current API integrations or stored data.
- Why is the status of text-embedding-3-small important for developers?
- Embedding models like text-embedding-3-small are used to turn text into mathematical vectors for semantic search. If a model is deprecated, developers must re-index their entire knowledge base because different models use different coordinate spaces. This clarification ensures that users do not have to perform expensive and time-consuming data migrations for their existing vector stores.
