Inference
Token
The basic unit of text that LLMs process.
In depth
The basic unit of text that LLMs process. A token is roughly 3-4 characters or about 0.75 words in English. Models have token limits for input (context window) and output (max completion). API pricing is typically measured per million tokens.
Example
In practice, developers reach for Token when they need the capability described above as part of an AI feature or workflow.
Go deeper at Developers Digest
Hands-on guides, comparisons, and tutorials that cover Inference.
FAQ
What is Token?
The basic unit of text that LLMs process.
Why does Token matter for AI developers?
Token sits in the Inference part of the AI stack. Understanding it helps you make better decisions when building, debugging, and shipping AI features.
Where can I learn more about Token?
Developers Digest publishes tutorials and videos that cover Inference topics including Token. Check the blog and YouTube channel for hands-on walkthroughs.
Related terms
Inference
Top-K / Top-P Sampling
Two methods for controlling the randomness of model output during token generation.
Inference
Tokenizer
The component that converts raw text into tokens (and back) for a language model.
Inference
Context Window
The maximum amount of text (measured in tokens) that a model can process in a single request.
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever