Glossary / LLM APIs and AI
Glossary · LLM APIs and AI · checked Oct 24, 2026
Embeddings
Short answerAn embedding is a list of numbers that represents the meaning of a text, so similar texts get nearby vectors. Search, RAG retrieval, clustering and duplicate detection run on them.
Why it matters
Embedding models are priced on input only and cost far less than chat models; the expensive part of RAG is usually the answer, not the search.
Our number
Our semantic cache experiment used embeddings to spot repeated prompts before they reach the model.
Go deeper on this site
Where it shows up here
It appears on 10 pages of this site: 6 Articles, 1 The Manual, 1 Guide, 1 path, 1 Report. A few to start with:
- Rust, LLMs, AI agents and app dev, with the receipts.
- LLM proxy benchmark: 200 duplicate calls became 1 (and a 30 s bug)
- The Manual.
- Step-by-step guides.
- LLM API Price Index, October 2026
- AI API costs, and how to cut them.
Sources
- OpenAI: embeddings guide: platform.openai.com/docs/guides/embeddings (checked Oct 24, 2026)
Related terms
Up next
Go deeperCheapest LLM for RAGThe page on this site that does the most with this term.Read it next →Did this answer your question?