Module · Intermediate
Models and parameters
Model families and how to choose between them, the parameters that change behaviour, multimodal inputs, embeddings and semantic search, and when reasoning models are worth their cost.
Models differ in price, speed, quality and abilities. This module gives you a vocabulary and a decision method, not a leaderboard.
- 1 Model families and how to choose Choose a model by matching its capabilities, response time, operating cost, and quality to the work you need done.
- 2 Parameters: temperature, top-p, max tokens Adjust model settings to balance variation, response length, and consistency without confusing those settings with factual accuracy.
- 3 Multimodality: images, audio, documents, video Choose how an assistant receives and produces media, and understand what can be lost when pictures, recordings, and documents become text.
- 4 Embeddings and semantic search Understand how numerical representations help find related ideas, where similarity can mislead, and how search supplies evidence to an assistant.
- 5 Reasoning vs standard models Decide when additional model reasoning is worth the waiting time and cost, and how to present useful explanations without relying on hidden thought.