1.3 Module 1 · AI Foundations & Mental Models

Tokens, Context Windows & Temperature

Three parameters that shape every AI interaction. Understand what they mean so you can control the outputs you get.

Temperature Slider Demo Context Window Comparator Token Cost Calculator

Temperature Slider Demo

Temperature controls randomness in token selection. Move the slider to see how different temperature values affect the output for the same prompt.

"Draft a one-sentence summary of Australia's AI policy position."

0.7
0.00.30.71.22.0

For Defence use: Keep temperature low (0 – 0.3) for factual summaries, data extraction, and policy drafting. Use moderate (0.5 – 0.7) for brainstorming and exploring options. Avoid high temperature for anything that will be presented as official output.

Context Window Comparator

The context window is how much text the model can consider at once — your prompt, any documents you paste in, and the response all share this space.

For government document analysis: Larger context windows mean you can paste in entire policy documents, Hansard transcripts, or legislative texts for analysis. But remember — performance can degrade with very long inputs, especially in the middle of the context. Place the most important content at the start or end of your prompt.

Token Cost Calculator

Estimate the cost of an AI query based on model, input size, and output size. Useful for budgeting enterprise AI deployments.

$0.00
Input Cost
$0.00
Output Cost
$0.00
Total per Query
At Scale
$0.00
100 queries
$0.00
1,000 queries
$0.00
10,000 queries

Procurement tip: Enterprise agreements typically include volume discounts. Most government use cases work well with mid-tier models (Sonnet, GPT-4o Mini) at a fraction of the cost. Reserve premium models for complex analysis tasks.