Token / word element
Token is the basic unit for model processing information; in text models, text is usually split into words, subwords, characters or byte fragments by a word segmenter. What is
Read article ↗TOKEN WIKI / Industry Knowledge Base
Understanding word elements starts with a concept.
has 52 introductory entries, starting from word units, computing power going overseas, and word units going overseas, covering models, reasoning, API billing and global delivery.
All termsword elements and billingcomputing power basismodel and inferenceinference performanceoverseas and architectureSearch and DiscoveryAI development toolsintelligent body and application
6 个词条
Tokenizer / tokenizer The
tokenizer converts the original text into a Token sequence that can be processed by the model, and restores the output Token into readable content.
Read article ↗input token
Input Token is the amount of information read by the model in a model request, which usually includes context such as user questions, system prompts, historical conversations, and tools.
Read article ↗output token
output token is the result usage generated by the model. Different services may also list specific usage incurred during inference.
Read article ↗Token cost calculation
Token cost calculation is the process of summarizing input, output and other billable items in the same currency and unit of measurement.
Read article ↗context cache
Context caching is a mechanism that reuses processed context when specific conditions are met to reduce repeated calculations.
Read article ↗