Token Economics

See all 11

What Are GPT-5.6's Sol, Terra, and Luna?

OpenAI shipped GPT-5.6 as Sol, Terra, and Luna on July 9, 2026, and quietly ended the dedicated Codex checkpoint. What replaced it is a reasoning-effort dial whose top notch spawns subagents. This post lays out the three models, the six effort levels, and what the independent benchmarks measured.

AI Systems Read in English

GPT-5.6 的 Sol、Terra、Luna 是什麼

GPT-5.6 在 2026 年 7 月 9 日全面上線，分成 Sol、Terra、Luna 三階，而這一代的 Codex 沒有專用模型。專用 checkpoint 換成一格叫 ultra 的 reasoning effort，官方說它會叫 subagent 出來把大任務拆開做。這篇整理三顆模型怎麼分、六段 reasoning effort 是什麼，以及幾份獨立評測量到的數字。

AI Systems 看中文版

How Many Tokens Is Your Prompt Actually Using?

Token counts land on your API bill and decide whether a prompt fits the context window. Here's why Chinese usually costs more tokens than English, why eyeballing it fails, and how to see the real number for any chunk of text.

AI Systems Read in English

你的 Prompt 到底花掉多少 Token？

Token 數會反映在你的 API 帳單，也決定一段文字塞不塞得進 context window。這篇聊為什麼中文通常比英文花更多 token、為什麼用猜的估不準，以及怎麼實際看一段 prompt 有多少。

AI Systems 看中文版

Does Saying 'Thank You' to ChatGPT Actually Cost Anything?

Sam Altman said people saying 'please' and 'thank you' to ChatGPT costs OpenAI tens of millions. I measured it with a tokenizer: your 'thanks' is two tokens. The real cost is the whole reply it forces.

AI Systems Read in English

跟 AI 說「請」和「謝謝」，到底有沒有差？

Sam Altman 說大家對 ChatGPT 講禮貌，燒掉 OpenAI 幾千萬美元。我用 tokenizer 實際量了一次：你那句「謝謝」只值兩個 token，真正貴的是它叫醒的整台機器。

LLM

See all 9

AI Systems 看中文版

跟 AI 說「請」和「謝謝」，到底有沒有差？

Sam Altman 說大家對 ChatGPT 講禮貌，燒掉 OpenAI 幾千萬美元。我用 tokenizer 實際量了一次：你那句「謝謝」只值兩個 token，真正貴的是它叫醒的整台機器。

Agent

AI Systems 看中文版

What Are GPT-5.6's Sol, Terra, and Luna?

AI Systems Read in English

GPT-5.6 的 Sol、Terra、Luna 是什麼

AI Systems 看中文版

Claude Fable 5: First Public Mythos-Class Model, One Day In

Anthropic released Claude Fable 5 on June 9 — the first publicly available Mythos-class model, one tier above Opus. What it is, what it costs, the June 22 deadline on the subscription window, and what changed when I pointed three real projects at it for a day.

AI Systems Read in English

Claude Fable 5 是什麼？第一個公開的 Mythos 級模型，加上我第一天的使用心得

Anthropic 6/9 釋出第一個公開的 Mythos 級模型 Claude Fable 5。這篇整理它跟 Opus 4.8 的關係、定價、6/22 截止的訂閱免費期，加上第一天把三個專案丟給它跑的心得：它對治理流程的遵守程度是真的，token 也是真的兇。

AI Systems Read in English

Token 成本的真相：分級，但別分太細

把 token 當設計變數而非月底帳單：太粗、沒在管的任務成本沒有上限，但分太細也不會更省。快取讓過度切分反而更貴，重點是找到對的顆粒度。

AI Systems 看中文版

Token Economics of AI Agent Governance

Governance has a bounded, knowable token cost; ungoverned agent work tends not to. And task granularity has its own price: caching can make over-decomposition cost more than it looks.

Governance

AI Systems 看中文版

Prompt Engineering

AI Systems 看中文版

Agentic OS

AI Systems Read in English

Token 成本的真相：分級，但別分太細

把 token 當設計變數而非月底帳單：太粗、沒在管的任務成本沒有上限，但分太細也不會更省。快取讓過度切分反而更貴，重點是找到對的顆粒度。

AI Systems 看中文版

Token Economics of AI Agent Governance

Governance has a bounded, knowable token cost; ungoverned agent work tends not to. And task granularity has its own price: caching can make over-decomposition cost more than it looks.