PromptForge
AI Glossary

Core concepts

Temperature

Also known as: temp

Definition

Temperature controls how random a model's word choices are. Low values (0-0.3) make output focused and repeatable; high values (0.8-1.2) make it more varied and creative but less reliable.

At each step a model produces a probability distribution over possible next tokens. Temperature reshapes that distribution before a token is sampled. At temperature 0 the model always takes the most likely option, making output nearly deterministic. Raising it flattens the distribution so less likely tokens get a real chance.

Choose by task, not by taste. Extraction, classification, code generation and anything a program will parse want low temperature — you want the same input to give the same output. Brainstorming, creative writing and generating multiple distinct options want higher temperature.

A common mistake is raising temperature to fix boring output. Usually the problem is a vague prompt, not insufficient randomness. Fix the prompt first; higher temperature applied to a vague prompt just produces varied vagueness.

Related terms

Put this into practice

Understanding the term is step one. Our free courses and tools let you actually use it.