Tokens Glossary

Browse 28 tokens terms defined in plain English, from the cultural dictionary of computing.

28 Tokens Terms

AI Token
A token as used by AI models, typically representing a chunk of text that counts toward context limits, cost, and generation length. Token counts matter...
API Token
A secret or signed token used to authenticate and authorize requests made to an API. API tokens vary in format and scope, but they commonly represent service...
Authentication Token
A credential or artifact proving that authentication has already occurred, allowing later requests or sessions to proceed without re-entering credentials each...
Context Window Limit
The maximum amount of input and generated token context a model can handle in one request.
ERC-20
The dominant token standard on Ethereum, defining a common interface (transfer, approve, balanceOf, etc.) that allows any compliant token to be traded, stored,...
Hardware Token
A physical token that generates one-time codes or performs secure cryptographic authentication for user access. Hardware tokens are widely used where stronger...
Initial Coin Offering
A fundraising method where a project sells newly issued tokens to the public or early participants, often before the product is fully mature. ICOs were a...
Input Token
A token consumed as part of the input to an AI model, counting toward context limits and often toward cost. Input tokens include prompts, instructions,...
JSON Web Encryption
JSON Web Encryption is the JOSE standard for encrypting claims or structured content into a compact token format. Security teams use it to enforce trust,...
JSON Web Signature
JSON Web Signature is the JOSE standard for integrity-protecting structured data with digital signatures or MACs. Security teams use it to enforce trust,...
LLM Token
A token as used in the context of large language models, counted toward prompt size, generation limits, and billing. LLM token usage is closely monitored...
Long-Lived Token
An access, refresh, or API token with a relatively long validity period before expiration or forced rotation. Long-lived tokens improve convenience and service...
Magic Cookie
A special marker value, token, or small piece of state that carries hidden significance in a protocol or system. In engineering slang, magic cookies are often...
Max Tokens
A setting that limits how many tokens a model may generate in a response or, in some systems, how large parts of the request can be. Max token settings help...
Model Token
A token as understood by a model's tokenizer and counted for context limits, billing, or generation length. Model token behavior matters because different...
Physical Token
A tangible object used in authentication or access control, such as a hardware OTP device, smart card, badge, or FIDO key. Physical tokens can improve security...
Prompt Token
A token consumed by the prompt portion of a model request, including system instructions, examples, user content, and retrieved context. Prompt token counts...
Reasoning Token
A token used during reasoning-focused generation or internal reasoning traces, often discussed in the context of cost, latency, or long multi-step responses....
Response Token
A token generated in the response portion of a model call. Response tokens are often tracked separately from prompt tokens because they influence output...
Thinking Token
A token associated with intermediate reasoning or extended deliberation in a model's generation process. The term is often used when discussing tradeoffs...
Think Token
A colloquial term for tokens consumed during hidden reasoning or intermediate internal processing in some model designs or product discussions.
Token Count
The number of tokens present in a prompt, response, document, or full model interaction. Token count affects cost, latency, and whether a request fits within...
Token Embedding
The vector representation associated with a token so the model can process it numerically rather than as raw text. Token embeddings are a foundational part of...
Token Generation
The step-by-step generation of tokens by a model during inference. Token generation speed and quality shape both latency and the final usefulness of the...
Token ID
The numeric identifier assigned to a token in a model's vocabulary. Token IDs are used internally by tokenizers and models to represent text as discrete...
Token Prediction
The act of predicting the next token or candidate tokens in a sequence based on prior context. Token prediction is the core mechanism behind many language...
Token Probability
The probability a model assigns to a particular token as the next output in a given context. Token probabilities are useful for scoring, confidence analysis,...
Token Sequence
An ordered sequence of tokens representing an input, output, or intermediate model state. Token sequences are the basic units many language models operate...

Related Topics