AI GLOSSARY · HOW IT WORKS
Latency
The delay between sending a request and getting a response.
Example
Fast inference providers reduce latency to under a second for short replies.
Learn it by doing
Reading a definition is a start; using the idea makes it stick.
Related terms
HOW IT WORKSTokenA chunk of text (often part of a word) that models read and write. Pricing and limits are counted in tokens.HOW IT WORKSContext windowThe maximum amount of text (in tokens) a model can consider at once, including your prompt and its reply.HOW IT WORKSInferenceRunning a trained model to get an output. Every chat reply is an inference call.HOW IT WORKSTrainingThe process of adjusting a model’s weights using data so it learns patterns.HOW IT WORKSTraining dataThe examples a model learns from. Its quality, coverage and bias shape what the model can do.HOW IT WORKSFine-tuningFurther training an existing model on a smaller, specific dataset to specialise it.