- Updated
- Version
- v1.1
- Sources
- 3 sources
- Status
- Published
text token
Token
A unit representing content processed by a model; in text, it may correspond to a word or a fragment.
Everyday phrases
- count context size
- why a word counts as several units
Key difference
A token is not always a word. Segmentation varies by model and language; use the appropriate counter rather than a page count.
Example
You measure an excerpt with the model’s counter before deciding which passages to supply.
Counter-example
Ten pages do not represent a fixed number of tokens regardless of content.
Continue with a guide
Related concepts
Sources
- https://ai.google.dev/gemini-api/docs/tokens
- https://ai.google.dev/gemini-api/docs/long-context
- https://platform.claude.com/docs/en/build-with-claude/context-windows
Revision glossary-v1.1:token · 2026-09-08
- Sourced content digest
- sha256:16e514031b0cba3864622fcad997c194b8321b37339c6c44b938851c72e01e19
Understand → Recognize → Choose → Compare
Pack for your agent
Pre-written instruction by SkillCodex — your request is neither sent nor used to adapt this text; no content is generated, and copying executes nothing.
Implement correctly
Use Token deliberately
# Ground Token in your agent ## Objective Use “Token” precisely in code, documentation, and conversations: A unit representing content processed by a model; in text, it may correspond to a word or a fragment. ## Prerequisites - Inspect how the term is used today in the repository, documentation, and prompts. - Identify the neighboring notions already named: Context window, Prompt. - Preserve existing correct usages. ## Working definition A unit representing content processed by a model; in text, it may correspond to a word or a fragment. ## Decisive difference A token is not always a word. Segmentation varies by model and language; use the appropriate counter rather than a page count. ## Example that counts as Token You measure an excerpt with the model’s counter before deciding which passages to supply. ## Counter-example Ten pages do not represent a fixed number of tokens regardless of content. ## Acceptance criteria - Every use of the term matches the working definition. - Edge cases are settled with the decisive difference, not by intuition. - Neighboring notions (Context window, Prompt) are named with their own term. ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.
- Requires · The agentic vocabulary already used in the repository and documentation
Why it works
- The notion is framed by a sourced working definition, not ambient usage.
- The decisive difference settles edge cases reproducibly.
- The example and counter-example bound the term on both sides.
Try next
Map the neighboring notions
# Map the neighboring notions ## Objective Extend the same rigor to the related notions (Context window, Prompt) so the project vocabulary stays coherent. ## Checks - List every neighboring notion used without a definition. - Apply its documented decisive difference. - Record the still-ambiguous cases for the next entry. ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.
sha256:a3a5af5540b8d2f6d6416c3e0c744b266d2a2764427341ce7af43b893fc196bf
Diagnose a problem
Fix a Token mix-up
# Fix a mix-up around Token ## Observed symptom [DESCRIBE THE SYMPTOM HERE] ## Observable checks - Compare the disputed usage with the working definition: A unit representing content processed by a model; in text, it may correspond to a word or a fragment. - Apply the decisive difference: A token is not always a word. Segmentation varies by model and language; use the appropriate counter rather than a page count. - Confront the case with the documented counter-example: Ten pages do not represent a fixed number of tokens regardless of content. ## Possible causes - The term is used for a neighboring notion (Context window, Prompt). - The observed form (interface, script, service) is confused with the actual behavior. - An alias (text token) carries a different meaning in the project. ## Bounded fixes - Rename or reclassify only the usages that contradict the working definition. - Document each choice by citing the decisive difference. ## Final verification - Reread every corrected occurrence against the documented example and counter-example. ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.
- Requires · The agentic vocabulary already used in the repository and documentation
Why it works
- The diagnosis compares usage with documented criteria instead of an opinion.
- Fixes stay bounded to genuinely contradictory usages.
- The final verification runs back through the sourced example and counter-example.
Try next
Anchor the vocabulary in the project
# Anchor the vocabulary in the project ## Objective Turn the clarification into a reusable rule so the mix-up does not return. ## Checks - Add the working definition to the project glossary. - Link every neighboring term to its own entry. - Check new documents against the decisive difference. ## Guardrails - Show the proposed changes before any external action. - Do not publish, send, delete, pay for, or change remote state without explicit authorization. - Preserve unrelated changes and stop if the scope becomes ambiguous. ## Output format - Outcome or verdict. - Files or actions involved. - Checks run and observable evidence. - Remaining blockers or limitations.
sha256:58929e3d910afc95cf55f7e62d4eefd8df652de283e23c9f2c7c5f772b88c859
Pack digest: sha256:ebbaeee624bd86820dbd77db8dc6c52064f23ac2f8da02cbcbc6571ba40e62a2