Token
Published Updated
What is Token?
A token is the unit of text a language model reads and writes, roughly a word or part of a word in English. Context limits, pricing and rate limits are all measured in tokens.
The fundamental unit of data processed by an LLM, roughly equivalent to a word or part of a word in English.
AI models do not read human text; they read tokens. A token is a chunk of text, typically consisting of about four characters or three-fourths of a standard English word. API costs, context limits, and processing speeds are all calculated based on the number of input and output tokens.
How it relates to Orbit
Orbit reports model usage and costs for agent runs and benchmarks in tokens. See Complexity Tiers & Routing for details.
When you would use it
You track tokens when managing the budget and performance constraints of an AI application, ensuring you don't exceed rate limits or exhaust the context window.
Common operations
- Calculating the financial cost of a specific API request.
- Determining if a document will fit inside a model's context window.
Frequently asked questions
How many tokens is a word?
On average about 1.3 tokens per English word, though code and other languages often use more.
Does Orbit show token usage?
Yes. Orbit reports usage and cost for agent runs and benchmarks, and shows live provider quota. See Quota & Cost Monitoring.