Comparison
Embedding modelvsLarge language model (LLM)
Embedding model
you pick a separate and far cheaper model whose output is a vector, and benchmark two candidates on your own documents before committing.
A model whose output is a vector rather than text. Separate from and far cheaper than chat models. Quality varies by domain and language, so benchmark candidates on your own data rather than trusting leaderboards alone.
Full entry →Large language model (LLM)
everything it does, the chat and the code and the reasoning, comes out of one trained habit of guessing the next token.
A neural network trained on enormous amounts of text to predict the next token in a sequence. Everything an LLM does, including chat, coding and reasoning, emerges from that single prediction task applied repeatedly.
Full entry →