LLM Glossary

Clear explanations of the terms you'll encounter when choosing and using LLMs.

Token

A token is the basic unit of text that LLMs process. One token is roughly 3/4 of a word in English.

Context Window

The maximum number of tokens an LLM can process in a single request, including both input and output.

MTok (Per Million Tokens)

The standard pricing unit for LLM APIs. $5/MTok means it costs $5 to process one million tokens.

Temperature

A parameter controlling randomness in LLM output. Lower temperature (0.0-0.3) gives more deterministic responses, higher (0.7-1.0) gives more creative ones.

Benchmark Grade

ModelPicker's rating system for LLMs. Models are scored 1-3 on 12 real-world tasks and graded as Weak, Usable, or Strong.

Cost Bracket

ModelPicker groups models into four price tiers based on output cost: Ultra ($10+/MTok), Mid ($2-10), Value ($0.50-2), and Budget (under $0.50).