Tokens icons

10 icons carry the tag tokens, across AI & LLM, Analytics and RAG & Search. Compress context, Context cache, Context length and 7 more — each in outline and duotone at three weights, with the code for React, Vue, Svelte, Flutter and more.

The 10 tokens icons, described

Compress contextcompress-context: The context window with chevrons pressing inward — the same content in fewer tokens.
Context cachecontext-cache: The context window with a block kept in it — tokens the model does not have to read again.
Context lengthcontext-length: Context length — how much fits between the brackets, the window in tokens.
Prompt compressprompt-compress: Prompt compression — fewer tokens carrying the same ask, squeezed to fit.
Reasoning budgetreasoning-budget: A coin held between brackets — the token budget a model may spend on thinking.
Streaming responsestreaming-response: A streaming response — the model's answer arriving token by token as it is written.
Token budgettoken-budget: The context window with a coin in it — how many tokens a call is allowed to spend.
Token pricetoken-price: Token price — what the words cost, each token as a coin on the bill.
Tokens usedtokens-used: A pill holding three tokens — the count of tokens a request consumed.
Vocabularyvocabulary: Vocabulary — every token piece the model can say, the full list.

In code, each is one import — import { CompressContext } from "@iconmind/react/icons/compress-context" — and the same name in Vue, Svelte, Solid, Preact, React Native, Astro, Blade and Flutter.

Tags these icons also carry

context23 budget17 all5 cache18 capacity14 coin6 compress10 cost32 count10 list34 live15 shrink11

Every tokens icon, free to ship

10 of 5,287 icons compiled from one grid — outline and duotone, three weights, every cell generated rather than redrawn. MIT licensed: commercial use, no attribution, no seat count.

All tags Install the package Request an icon