What is…

Temperature

A setting that controls randomness — low for precise, repeatable answers; high for creative variety.

When a model picks its next token it has a list of candidates with probabilities. At low temperature it almost always takes the top choice (consistent, predictable). At higher temperature it samples more adventurously (varied, creative, occasionally weird).

Chat apps set this for you; APIs and playgrounds let you adjust it. Data extraction: low. Brainstorming names: higher.

🧠 Test yourself

Which of these describes Temperature?

Related terms

LLM (Large Language Model)

A model trained on huge amounts of text to predict the next word — the engine behind ChatGPT, Claude, Gemini and Grok.

Inference

Running a trained model to get an answer — as opposed to training it.

🎮 Learn AI by playing

40 bite-size missions, boss battles and a certificate. Free.

Start the bootcamp →

☀️ One AI term every morning

Plus the day's top stories, in your inbox by 8am.

← System prompt Few-shot prompting →