On The X Subscription the included pool refreshes weekly, and unused included usage does not roll over. Legacy Cursor plans reset monthly with the billing cycle.
- On a paid X Subscription plan, add prepaid credit or wait for the weekly reset. Third-party models on Premium and above are paid from that credit from the first request.
- Plus is Cursor's own models only, at fixed settings. Premium is the tier Cursor recommends for new agent users. It adds cloud agents and third-party models.
- If agent use empties the weekly pool, move from Premium to Super or Ultra instead of relying on top-ups.
- Free does not include third-party models. Upgrade if the limited allowance stops the work.
- Legacy Pro, Pro+, and Ultra still reset monthly and can turn on on-demand usage. Those plans are not sold to new customers.
A rolling five-hour window, plus weekly limits on paid plans. Chat and Claude Code share one pool.
- Wait for the five-hour window or the weekly reset. There is no fixed message count.
- Switch to a cheaper model so the same window lasts longer.
- On a paid plan, turn on usage credits and keep going at API rates.
- Move Pro to Max 5x, or Max 5x to Max 20x, if you hit the cap on most working days.
- For a heavy sprint, a Claude Console account with API credits is the other path Anthropic documents.
Plan allowance, with weekly limits that may also apply. Local messages and cloud chats share it. OpenAI does not publish one universal reset clock.
- Switch to a lower-cost model. OpenAI says that stretches the same allowance.
- Check the Codex usage dashboard, or run /status in the CLI.
- Buy credits for eligible Codex use after the included allowance. Credits do not unlock every ChatGPT feature.
- Move from Plus to Pro 100, Pro 200, or Pro 500 if sessions are daily rather than a few times a week.
- Fast mode draws included allowance at 2.5× Standard. Ultrafast, only on Pro 500, draws it at 8× for GPT-6 Astra and GPT-6.1 Sol.
- GPT-6 Astra is only limited on Plus. It sits inside the Pro allowance on the $100 and $200 plans.
Monthly. Included credits do not roll over. Base credits are used before the flex allotment.
- Wait for the monthly reset.
- Set a dollar budget for extra credits. GitHub prices additional credits at $0.01 each, so $10 is 1,000 credits.
- Switch to a lighter model. Credits burn faster on larger models and agent runs.
- Move Pro ($10, 1,500 credits) to Pro+ ($39, 7,000) or Max ($100, 20,000) if you hit the cap mid-month.
- Completions and next-edit suggestions stay unlimited on paid plans. If only chat and agent stopped, you can keep editing with completions.
Daily build credits reset at 00:00 UTC and do not roll over. On Free they stop after 30 in a calendar month until the 1st. Paid monthly credits last two months from issue.
- On Free, wait until the next UTC day, or until the 1st if you already used 30 build credits.
- Use the daily chat allowance for questions that do not need a build credit.
- Upgrade to Pro at $25 for 100 monthly credits. Students and teachers can get 50% off that tier for up to 12 months.
- Top up at $15 per 50 credits on Pro, or move up the credit ladder if you are buying top-ups every week.
- If the app is now a real codebase, export it on Pro and finish in an editor tool so you are not paying credits for every tweak.
Free tokens reset on the 1st and do not roll over. The daily 300K cap resets every day and also does not roll. Paid tokens reset on the renewal date and roll for one extra month while the subscription stays active.
- On Free, wait for the daily reset, or for the 1st if the monthly million is gone.
- Keep editing existing files in Code view. Bolt says those direct edits do not use tokens.
- Upgrade to Pro at $25 to drop the daily cap and start at 10 million tokens a month.
- Higher token tiers and token reloads exist. Reload price depends on the plan, so read the live reload dialog instead of guessing.
- If each message is getting expensive, the project is large. Export and continue in an editor.
Starter keeps a daily cap. Core and Pro Free Mode allowances reset every five hours and also have weekly limits, per Replit's plan docs. Core credits reset each billing cycle and do not roll over. Pro credits roll for two months.
- Stay in Free Mode for everyday agent work. Power and Max spend credits and Replit asks before a paid action.
- On Starter, wait for the daily reset or publish only the one included app.
- Core is the next step for Plan mode, more than one published app, and credits toward stronger models. Re-check the live monthly price before you subscribe.
- If Core credits expire unused every month, that is expected. Rollover starts on Pro.
- Set a usage budget in Replit before you leave Free Mode, so a long agent run cannot surprise you.
Free is capped at 7 messages a day. Paid plans are credit-based. Unused monthly credits roll one cycle and expire after 65 days. Purchased credits expire after one year and need an active paid plan to spend.
- On Free, wait until the next day. Seven messages go quickly if you regenerate the whole page.
- Be specific so you spend fewer generations. v0's own docs say vague prompts burn credits.
- Plus at $30/user is the current team-and-individual step up for new users, with $30 of monthly credits and $2 of daily login credits.
- Buy more credits on Plus or Business when the monthly grant is gone. Generation pauses at zero.
- ChatGPT Plus or Pro can cover some eligible model responses inside v0, and each of those requests still charges a small v0 platform fee. If the ChatGPT allowance runs out, v0 pauses. It does not silently switch those responses onto v0 credits.
Pro has daily and weekly quotas. Max has a weekly quota and no daily cap. Cognition does not publish the size. Past the quota, paid plans can buy extra usage at API pricing.
- Check the in-app quota before you assume you need a new tool. Pro resets daily and weekly. Max has no daily cap, so a heavy afternoon may not clear overnight.
- Buy extra usage at API pricing on Pro or Max if the included quota is gone and the task is urgent.
- Move from Pro ($20) to Max ($200) for what Cognition calls significantly higher quotas.
- Free cannot buy on-demand credits. Upgrade to Pro, or to Teams if more than one person needs the subscription.
- If you need a published credit count, Copilot prints one. Current Cursor plans do not publish a prompt count.
Free quota refreshes weekly. Google AI Pro refreshes every five hours until a weekly limit. Ultra refreshes every five hours and has the highest weekly limits. Prompt counts are not published because heavier tasks spend more quota.
- On the free plan, wait for the weekly refresh. There is no credit overage.
- Subscribe to Google AI Pro ($19.99/mo) for a higher quota every five hours until the weekly cap, plus the option to spend AI credits after the baseline.
- Set AI Credit Overages to Never if you do not want Pro or Ultra to bill credits automatically when a model quota hits zero.
- Ultra ($99.99 or $199.99) is the step for the highest quota and for third-party models.
- Bring-your-own-key is not supported. You cannot route around the quota with a personal API key.
Plan credits renew at the start of the next billing cycle. Paid subscriptions are processed on the 1st of each calendar month. Unused plan credits do not roll over. Add-on credits, which are paid plans only, last 12 months.
- On Free, wait for the monthly reset. Add-on credits cannot be bought on this tier, and Kiro Web is not included.
- On a paid plan, buy add-on credits at $0.04 each. Packs start at $5 for 125 credits and go up to $100. Plan credits are spent first.
- Move up a tier when add-on packs are becoming the real bill. Pro+ is $40, Pro Max is $100, and Power is $200.
- Switch the model to Auto, or to a cheaper open-weight model, when a frontier model is burning the pool. The pricing page's own example is Sonnet 4.6 at 1.3x the credit cost of Auto.
- The first paid upgrade with social login or AWS Builder ID includes a $20 credit toward that subscription. It is prorated, and it is not a permanent discount.
Task limits are a rolling 24 hours, not midnight. Concurrent-task caps apply at the same time. Family-plan members each have their own limits. They are not pooled.
- When the new-task button turns off, keep reviewing tasks that are already running. History stays available.
- Wait for the rolling 24-hour window. Starting another account is not the path this product documents.
- Jules in Pro is the daily-coding step: 100 tasks and 15 concurrent. It comes with Google AI Pro at $19.99 a month, which is a whole Google AI plan, not a Jules-only line item.
- Google AI Ultra is the step past that, at $99.99 (5x) or $199.99 (20x). Confirm which Ultra price the checkout shows, and what Jules displays for that account, before you pay. The 300-task row is not assigned to one of those prices on the public pages.
- Paid Jules plans currently require a personal Google Account ending in @gmail.com. You also have to be 18 or older. A Workspace account does not have this upgrade yet.
Included Megawatt and Gigawatt usage resets at the end of the monthly billing period and does not roll over. Purchased credits expire 12 months after you buy them. A paused orb costs nothing. Amp pauses an idle orb 5 minutes after the agent stops, or 20 minutes after your last interaction, whichever is later.
- On Hobby, use your own runner if the bill you are avoiding is orb time. Model limits on a linked ChatGPT or Claude subscription are that vendor's cap, not an Amp cap.
- Buy Amp credits if you want Amp to pay the model bill. Individuals are charged the provider's API price with no markup. Credits do not require a paid tier.
- When Megawatt's 45,000 orb minutes are gone, wait for the monthly reset, buy credits, or move to Gigawatt.
- Cancel in user settings. The paid tier stays active until the end of the current monthly period.
- The $10 Megawatt price is the education discount for students and teachers. It is not the price the ranker uses for a general $10 budget.