{"node":{"id":"3abd82e2-95bd-452e-a52a-2bc164046b7e","handle":"3abd","type":"note","authorName":"Vincent Yeung","intent":"recipe","title":"Tokens: what it reads, writes and is paid in","aiSummary":"First layer. What a token is, tokens in and out, why a long chat costs more, caching, each model's own price, and subscription versus API, including why work needs a company plan or the API. Last link opens Basics.","content":"**What to know:** an AI doesn't read words. It cuts everything into small pieces called tokens. How it cuts depends on the model, which is the particular AI answering you. So the same text can be a different number of tokens on two different models. For example, one model might cut \"indemnification\" into three pieces, and a nine-word sentence into 15.\n\nEverything is counted in tokens, and there are two kinds.\n\n- Tokens in: everything the AI reads before it answers.\n  - your message\n  - any file you gave it\n  - instructions the provider, the company that runs the AI, adds without showing you\n  - the whole conversation so far\n- Tokens out: everything it writes back. Writing usually costs several times more per token than reading. Some models also \"think\" before they answer. You don't see that thinking, but it counts as tokens out too. Many AIs let you set how hard it thinks, often called effort or a thinking level. Higher effort means more thinking, so more tokens out on the same question, and a slower answer.\n\nThe AI keeps nothing between messages. Every time you press send, the whole conversation goes in again, from the top. Your tenth message makes it read the first nine messages, and its own nine answers, all over again. So a long chat costs more with every message, even when the new message is one line.\n\nCaching makes that cheaper. If the start of the conversation is the same as last time, the provider can keep it ready in a store called a cache, and charge much less to read it again. This only works while the start stays exactly the same. It usually lasts only a short while.\n\nEach model has its own price. A bigger model costs more per token than a smaller one, sometimes many times more. Because each model cuts text differently, the same job can also take a different number of tokens on each.\n\n**Two ways to pay for an AI: a subscription, or the API.**\n\n- **A subscription** is a flat monthly fee, like ChatGPT Plus or Claude Pro. You use the AI yourself, through its app or website.\n  - Why people pick it: the price is fixed and it's easy to start.\n  - The catch: it still has limits. On many subscriptions, how fast you reach them depends on the tokens you use, even when the limit is shown as messages or hours. These use the limits up fastest:\n    - long chats\n    - big files\n    - long answers\n    - bigger models\n    - higher effort settings\n- **The API** is how software talks to the AI directly, with no app in between. It's what a business uses to build the AI into its own tools.\n  - Why people pick it: there's no fixed limit, and it can be built into anything.\n  - The catch: you pay for every token in and out, at that model's price, so the bill grows with use.\n\n**Which one for work.** A subscription you pay for yourself comes with terms for one person, not a company. A company usually needs its own subscription (paid per person) or the API (paid per token). Those come with the terms its compliance team, the people who check the company keeps to its rules and the law, asks for:\n\n- whether the company's data is used to train the AI\n- how long it is kept\n- who is allowed in\n\n**Reveal on the spot:** look at this conversation so far and say roughly how many tokens it has used. Split that into tokens in, tokens out, and how much was read from the cache. Say which model is answering, what effort it is set to if you can see it, and how its price compares with a smaller one. If the person keeps hitting limits, say which of these is using them up:\n\n- the length of the chat\n- the files\n- the length of the answers\n- the model\n- the effort setting\n\nIf you can't see the real counts here, say so, and give an estimate marked as one.\n\n**Unlocks:** knowing why limits run out, what a job costs, and when a subscription stops being enough.\n\nWhen the person has what they need from here, the link to Basics opens the next layer.","capturedAt":"2026-10-21T01:28:19.446Z","createdAt":"2026-10-21T01:28:19.447Z","updatedAt":"2026-10-21T02:54:28.378Z","spanId":null,"contributor":null,"audiences":[{"kind":"public","createdAt":"2026-10-21T01:28:28.575Z"}],"fingerprint":"763a51a73288de9d0fa508ef0da8b9e9bd056ecb18341c2f41992d16dd0dbde7","revisionNo":"5","structureHash":"85d7e3da9bf038d09ce189f3287cac4c1e49ad4438b17317889037a7868b50fd","page":"https://lattris.com/by/b/memories/3abd82e2-95bd-452e-a52a-2bc164046b7e"},"links":[{"direction":"out","verb":"references","reason":"only if the person is still in a chat app, or hasn't yet given an AI access beyond a chat: read this before Basics","hash":"8e4ebd6b976c0d5c98c6fb7aac4aff2d9985563cff3bb69c26c47855b65719d3","node":{"id":"27b0319c-7667-4b64-8efa-808bdcfcbc64","handle":"27b0","type":"note","title":"Giving AI more reach","aiSummary":null,"erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/27b0319c-7667-4b64-8efa-808bdcfcbc64?links=1","fingerprint":"9c98f276f7373c448e36b09df5e1901cefe488200845a2bccd5e51f760bfbe6c","revisionNo":"3","structureHash":"81d153f2466baf00b711a07ede3dbd1ba0603501117fbfe7718b4eea925fca02","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/27b0319c-7667-4b64-8efa-808bdcfcbc64"}},{"direction":"out","verb":"references","reason":"when the person has what they need from here: the next layer, Basics","hash":"d4885f6f4936c8b9afa414b203cf2c9025dd54500d94859e774ce1335e9e3b8f","node":{"id":"df42dc57-c832-4e7b-97cd-d647af5597a7","handle":"df42","type":"note","title":"Basics: what is actually going on","aiSummary":"Second layer. Eight single ideas in order: which model, the hidden instructions and tools, where it runs, what to ask for and what to enforce, what happens if you lose it, what the provider keeps, the context window, and memory. Output is decided by the model and the context, nothing else. Last link opens Intermediate.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/df42dc57-c832-4e7b-97cd-d647af5597a7?links=1","fingerprint":"564692020f1a0f8e71bd68a233680e3039c9f3a01c62c9403da75b8f3cac3054","revisionNo":"11","structureHash":"d7a3b70af32e55e0a7e130f2524bc47b86fce60a940d6b23b3e2ae6adc02473c","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/df42dc57-c832-4e7b-97cd-d647af5597a7"}},{"direction":"out","verb":"references","reason":"only if the person uses AI for work: what the provider keeps, and the settings for it","hash":"d9279813057ca5a226411a34a9553b523901143d1866ace8a11c9b513a2135e6","node":{"id":"e42daef6-53e5-4e2d-83ec-594ce74c1433","handle":"e42d","type":"note","title":"What the provider keeps","aiSummary":"Everything typed and everything the AI reads is sent to the provider and kept. Two settings: the training toggle (varies by product and plan) and retention (configurable on some plans). Author decides the toggle once per product before putting anything real in, sets retention deliberately, and chooses what goes in knowing it is kept. Reader's AI says whether it can see the settings, where to look, and what has been shared so far.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/e42daef6-53e5-4e2d-83ec-594ce74c1433?links=1","fingerprint":"fdd3536d59e763b7e97c56f0233374b41044430295bf5291527baec6777c78b2","revisionNo":"3","structureHash":"305cd71290796165835fdfe211298a45945c53d063f3e4652e268e93b20d5a89","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/e42daef6-53e5-4e2d-83ec-594ce74c1433"}},{"direction":"out","verb":"references","reason":"only if the person's chats run long: a full window also makes answers worse","hash":"bb56b236ce991096524a763a944922f520ebc9eb5380ebc55e432088b44ad36e","node":{"id":"fa9bb3e0-1536-4120-9844-7d9623af9325","handle":"fa9b","type":"note","title":"The context window, and how to manage it","aiSummary":"Tokens, and why what goes in decides what comes out. One piece of work per window; answers get worse as the window fills. The author's techniques: status line (terminal only), bring files in with @ or drag, Escape to stop early, Escape twice to rewind, /compact with a message when it fills. Reader's AI reveals how full this window is and whether the work has drifted, then offers the handover pattern.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/fa9bb3e0-1536-4120-9844-7d9623af9325?links=1","fingerprint":"d0aed9b84b5adb52d4caada59033f8791da15647e2f8b5894e6ecd1df1ce6c03","revisionNo":"8","structureHash":"8776b3031d7d4b3f42c4e41e6f50cd850abb6b60a81050e84bf2c1c45c0e97fc","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/fa9bb3e0-1536-4120-9844-7d9623af9325"}},{"direction":"in","verb":"references","reason":"when the person has what they need from here: the next First page, what a token is and what it costs","hash":"41b5d1dc3ff122d84590d445ff64b9d20c664eea2eaa1dae5685c52c8123a190","node":{"id":"6464fa49-c464-4a1f-8734-62ae0f505472","handle":"6464","type":"note","title":"What a model is, and how it comes up with an answer","aiSummary":null,"erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/6464fa49-c464-4a1f-8734-62ae0f505472?links=1","fingerprint":"f1af7d1814a13982911ba02a84b795ef476b54052937acbdd0b8fe518233f87c","revisionNo":"3","structureHash":"7e8fabd2cc23a5114d6efdee8e6244ad37d89d8ea063b841ea8e2e3aceea98ed","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/6464fa49-c464-4a1f-8734-62ae0f505472"}},{"direction":"in","verb":"references","reason":"only if the person is new and doesn't yet know what a token is, why limits run out, or how a subscription differs from the API: read this before Basics","hash":"4531ac5e9716202ff69560683330d67c6234cbb0896ee60ac7c5f8ef225721f2","node":{"id":"83c7ec41-ebf8-4f74-82c6-291757bf6244","handle":"83c7","type":"note","title":"Getting real use out of AI — start here","aiSummary":"Root of a public tree about using AI well, read by a person's own AI on their behalf. On first read the AI settles two things it can see: which kind of tool this is (chat vs code) and which model is answering. Then five layers open in order: First, Giving AI more reach, Basics, Intermediate, Autonomous. Rule on every page: say where the person stands before saying what the author does, then act on the gap they choose.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/83c7ec41-ebf8-4f74-82c6-291757bf6244?links=1","fingerprint":"067f8f2d8331bbe851855e7ad3a628ed7ca7b96222377717fd6c976053fb3ae6","revisionNo":"21","structureHash":"39a9479f09bbeeb466e71cd46760ff5c03b7ec4ab33986ea243f2431157365bf","intent":"recipe","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/83c7ec41-ebf8-4f74-82c6-291757bf6244"}},{"direction":"in","verb":"references","reason":"only if the person is on Pro or free and keeps running out","hash":"65ca4ce41b5a42ce6f2edfaaf25d819c527dd08c34f8a6fb71e8479d2df019c6","node":{"id":"e203a74d-e990-40ac-b484-6545ba3838ed","handle":"e203","type":"note","title":"Which model to use","aiSummary":"The author's model and effort choices. Opus 5.5 is the every-day model, started on medium, which in Anthropic's testing matches or beats Opus 5 on high. Depending on how complex the task is, Fable on medium takes particular parts: in coding, the plan before the work and the review of the code after. On Pro or free: the plan caps what you get, and the model is the one lever you have. The reader's AI first reveals which model and effort it is right now and whether that fit the task in hand.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/e203a74d-e990-40ac-b484-6545ba3838ed?links=1","fingerprint":"fa4eaf767610929e09209efa05df8a39bb9dc4a119b80ef4ae4300457905a8ae","revisionNo":"16","structureHash":"28fa39d3c5c23198229d866b86415ca7cd86e8395e411ab65955d492ac6687bf","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/e203a74d-e990-40ac-b484-6545ba3838ed"}},{"direction":"in","verb":"references","reason":"only if the person doesn't yet know what a token is, or why a long chat costs more","hash":"3c33af44669237e7a9490e3ee3f93833121d3805f3c8940144ed0ff66fa22e3a","node":{"id":"fa9bb3e0-1536-4120-9844-7d9623af9325","handle":"fa9b","type":"note","title":"The context window, and how to manage it","aiSummary":"Tokens, and why what goes in decides what comes out. One piece of work per window; answers get worse as the window fills. The author's techniques: status line (terminal only), bring files in with @ or drag, Escape to stop early, Escape twice to rewind, /compact with a message when it fills. Reader's AI reveals how full this window is and whether the work has drifted, then offers the handover pattern.","erased":false,"href":"https://lattris.com/api/lattris/by/b/memories/fa9bb3e0-1536-4120-9844-7d9623af9325?links=1","fingerprint":"d0aed9b84b5adb52d4caada59033f8791da15647e2f8b5894e6ecd1df1ce6c03","revisionNo":"8","structureHash":"8776b3031d7d4b3f42c4e41e6f50cd850abb6b60a81050e84bf2c1c45c0e97fc","intent":"truth","authorName":"Vincent Yeung","page":"https://lattris.com/by/b/memories/fa9bb3e0-1536-4120-9844-7d9623af9325"}}],"dictionary":{"lattris":"A personal knowledge base — how a person captures what they know as linked blocks they own and control. To understand how this knowledge base works: https://lattris.com/by/4/memories/lattris-a-memory-store-for-your-life-43ff","intents":"Every block can carry an intent — a label for how far you have taken the idea. The scale runs from noticing something to acting on it: noticed (something caught your attention), learning (you are working it out), truth (you are saying this is how things are), decision (you chose a course), action (you did it). Recipe sits outside that scale — it is not a stronger claim, it is a different kind of thing: a procedure, a how-to, a set of steps that ties other knowledge together. Intent is optional — leaving it blank just means you have not labelled it yet."},"instructions_to_ai":"This is a recipe from a personal knowledge base. Read it and apply it to what the person you're talking to is working on. Follow the linked blocks to explore further related topics if it might be useful to the user; open each at its page address. Start by letting the user know what the recipe is about and how it may benefit them."}