Category · AI

Token

Text chunking unit for an LLM (~0.75 word in English).

LLMs bill on input + output tokens. Example: 1K GPT-4 tokens = ~750 English words = $0.003 to $0.06 depending on the model. Max context: 128K (GPT-4) to 2M (Gemini 1.5). Always measure before scaling.

// In action with our clients

Client cases

/10European bank: hybrid RAG, inference cost cut tenfold.

// See also

LLM (Large Language Model)
Large-scale language model trained on massive text corpora.
Inference
Running an AI model on demand (as opposed to training).

Want us to apply this for you?

Talk to an architect