claude现在好快就达到limit

上个月的时候,免费用户一天差不多可以问七八个问题 最近这一周,基本一个问题就立马limit了,甚至本来给的output又给吞了回去… 有人开20 usd一个月的subscription了吗 大概一天能用几个问题啊 chatgpt一个月20 USD,我基本上从来没有用到过limit

3a0587: 免费用户 claude的免费用户真的有任何quota吗，我感觉pro都秒达上限，必须max 5x起步才能获得和别家20刀subscription相近的quota

免费是这样的，防蒸馏如防贼

这也太夸张了 phd student 用不起咋办 但是chatgpt分析数据确实比claude差不少,把数据feed 给claude, claude立马就产出很精美的图表,分析,结构化阐述

3a0587: chatgpt一个月20 USD,我基本上从来没有用到过limit chatgpt感觉没有任何limit吧？？或者降智了我都不知道

Alila: pro都秒达上限 这能问几个问题

3a0587: phd student 用不起咋办 可以用codex（虽然codex现在额度也降了），实在不行就量大管饱的GLM coding plan，反正智谱蒸的也是Claude 20岁了还没去过星巴克: 这能问几个问题 感觉claude code两三轮对话就达5小时上限了

同时用claude的pro和chatgpt的plus，都是20刀，一个项目互相review，claude达到5h limit的速度差不多是chatgpt的5倍

人在美国,账号也是美国账号,IP也是学校的IP,就是正常使用

你也是phd student吗 这下每个月都要自掏腰包40 USD用来订阅AI了 gemini我感觉就是比较更新快比较有fact check,但是做research上用处还是不太大

3a0587: phd student 用不起咋办 100块一个月claude max为啥用不起…还好吧，你的stipend应该还是够的

200刀Max也比之前消耗快，目测快40%

stipend确实够 但是有点心疼 wallet 但是看见peers papers哗哗地出来,似乎也不得不多花钱了

我的stipend里固定这100块是给claude max的，其他地方能克扣一点

3a0587: gemini Gemini感觉更新太慢了，去年10月的时候感觉3 Pro的knowledge和reasoning很强，但之后基模tool call优化这一波没有跟上，导致现在和Opus-4.6 GPT-5.4是有代差的 3a0587: stipend确实够 但是有点心疼 wallet 至少北美还能用，昨天Claude的身份验证新政策出来国内的朋友圈哀鸿遍野 以后想用Claude得先拿个美国驾照

这是故意的吗

gpt确实是有的 但是量很大 基本上用不到 claude我上次一个小时就干完了

3a0587: gemini我感觉就是比较更新快比较有fact check 感觉信息最正确的是grok？

借楼问一下，claude pro 开5个号，是不是比5x套餐好

quota理论上一样的，实际上max我猜没5个pro多，但五个号切来切去不费劲么

我得向你学习Leo这个钱确实应该花，而且花的值得

Alila: pro Alila: claude code两三轮对话就达5小时上限 也就是max也只能问是十几个问题？

5个号的话，我不用时还可以给不同的朋友用啊，也防封号。

我感觉claude写software已经太容易了，你把spec给他写好，直接秒了。确实对科研帮助很大，现在想idea就行了，等于找一个SDE给你打工，你自己就是博导

可以用gemini吧 虽然感觉比claude弱一点但没有限量

靠着codex和claude我可以一个小时搞完一个qwen的lora的pipeline 放以前这种代码量不得搞至少一周 效率提升太显著了

我以前也以为ChatGPT人性化，结果发现更阴险。ChatGPT是按月算的Limit，最开始你以为没有limit，可以一直用，到了Limit就给你降级，然后下个月才能恢复。Claude起码是写的清清楚楚你还有多少Limit

那可不是弱一点，是弱很多，而且也会达到限量

claude会员比起chatgpt还是良心

建议用max，200 块问问能不能老板报销，效率差好多

免费的chatgpt team已经说累了，无限的token，不要钱 https://www.uscardforum.com/t/topic/398026 /c/shopping/20 Update: 新用户有机会0元开通，没有的直接开个新账号 Update2: 更新新用户0元开通的流程以及截图 Update3: 更新开通链接 Update4: 可以使用CPA通过codex的额度把pro转成API使用 Update5: 提前取消会直接被cancel trial old 薅完记得取消订阅 不能提早取消 确定提前取消会直接整个trial cancel 提前取消会被… 觉得claude code付不起为什么不试试

https://chatgpt.com/codex/settings/usage 人家把用量和什么时候reset写的清清楚楚，你上去查一下不就知道了。 Codex反正是按周reset额度的，不是按月

pro 20刀没用的，真要生产力至少 max 5x 100刀的起，要想用的舒服就 20x 200刀。 看分析 5x 比 5 个 pro 量要多，但是 20x 没有 4 个 5x 量多。

如果是20刀的tier codex体验要比cc好太多 用opus可能五个来回就没了

找老板帮你开20x

垃圾公司 自己拿着开源的资料大抄特抄 然后闭源还不让别人蒸馏 暗地里偷偷摸摸浪费用户token变相加价 /uploads/short-url/zs92rQwAhZkcHyjkBl8UOJ353Ya.jpeg?dl=1

100 刀也不太够 了，5h 的 limit 不够，week 倒是够用。这样实在不太想开 200，准备投奔 codex 了

单看数值 Max 5x 是性价比最高的方案

/uploads/short-url/dwBfS6u5HoJsyXMXx9QjA4MD7nX.png?dl=1 用opus的时候尤其快

插队问个问题, Claude code 和 Codex 同档次比较 Claude code 感觉要慢很多. 大家是不是也是这么觉得的 公司不让用Codex 在家又不想开Claude code 没法做apple to apple的比较

现在claude code好像是动态订limit，早上高峰期limit很快就到，下午晚上可以用久一点。

建议尽快转OAI或者的模型。反人类学喜欢当用户爹。后面指不定怎么拿捏大家。

以后token和广告一样, 都real time bid

我靠思路牛逼啊。

浮动定价，美联储积分愉快贬值

企业账号会被封禁吗，一直好奇 最近总是频繁让我登录

按反人类学的操行，你整个周期被封的概率肯定无限接近1。毕竟五角大楼都敢封的公司。

Rosmontis: 浮动定价 反正互联网公司就是nb, 今天差点误了定的uber, 然后在uber上查waiting fee怎么算. 居然告诉我根据算法决定等多久开始收费, 罚多少钱, 都不明码标价的

互联网公司真的把计划经济做成功了。

压根不怕，我们提供的免费账号，真封了找管理员去

现在直接买 API，一个月 200-300

3a0587: phd student 用不起咋办 csr cse plat马上要加福利了

https://github.com/anthropics/claude-code/issues/46829 https://github.com/anthropics/claude-code/issues/46829 已打开 01:49AM - 12 Apr 26 UTC 已关闭 10:15AM - 12 Apr 26 UTC https://github.com/seanGSISG bug has repro area:cost api:anthropic # Cache TTL appears to have silently regressed from 1h to 5m around early March 2026, causing significant quota and cost inflation ## Summary Analysis of raw Claude Code session JSONL files spanning Jan 11 – Apr 11, 2026 shows that Anthropic appears to have **silently changed the prompt cache TTL default from 1 hour to 5 minutes sometime in early March 2026**. Prior to this change, Claude Code was receiving 1-hour TTL cache writes — which we believe was the intended default. The reversion to 5-minute TTL has caused a **20–32% increase in cache creation costs** and a measurable spike in quota consumption for subscription users who have never previously hit their limits. This appears directly related to the behavior described in #45756. --- ## Data Session data extracted from `~/.claude/projects/` JSONL files across **two machines** (Linux workstation + Windows laptop, different accounts/sessions), totaling **119,866 API calls** from Jan 11 – Apr 11, 2026. Each assistant message includes a `usage.cache_creation.ephemeral_5m_input_tokens` / `ephemeral_1h_input_tokens` breakdown that makes the TTL tier per-call observable. Having two independent machines strengthens the signal — both show the same behavioral shift at the same dates. ### Phase breakdown | Phase | Dates | TTL behavior | Evidence | |-------|-------|--------------|----------| | 1 | Jan 11 – Jan 31 | **5m ONLY** | `ephemeral_1h` absent/zero — likely predates 1h tier availability in the API | | 2 | Feb 1 – Mar 5 | **1h ONLY** | `ephemeral_5m = 0`, `ephemeral_1h > 0` across **33+ consecutive days** on both machines — near-zero exceptions | | 3 | Mar 6–7 | **Transition** | First 5m tokens re-appear, small volumes, 1h still present | | 4 | Mar 8 – Apr 11 | **5m dominant** | 5m tokens surge to majority; 1h becomes minority or disappears entirely | We believe Phase 2 represents Anthropic's **intended default behavior** — 1h TTL was rolled out as the Claude Code standard around Feb 1 and held consistently for over a month across two independent machines on two different accounts. January's all-5m data most likely predates the 1h TTL tier being available in the API. The regression began **around March 6–8, 2026**. No client-side changes were made between phases. The same Claude Code version and usage patterns were in place throughout. The TTL tier is set server-side by Anthropic. ### Day-by-day TTL data showing the regression (combined, both machines) ``` Date | 5m-create | 1h-create | Behavior ------------|------------|------------|---------- 2026-02-01 | 0.00M | 1.70M | 1h ONLY ← 1h default begins 2026-02-09 | 0.00M | 7.95M | 1h ONLY 2026-02-15 | 0.00M | 13.61M | 1h ONLY ← heaviest day, 100% 1h 2026-02-28 | 0.00M | 16.15M | 1h ONLY ← 16M tokens, still 100% 1h 2026-03-01 | 0.00M | 0.12M | 1h ONLY 2026-03-04 | 0.00M | 8.12M | 1h ONLY 2026-03-05 | 0.00M | 6.55M | 1h ONLY ← last clean 1h-only day | | | 2026-03-06 | 0.29M | 0.22M | MIXED ← first 5m tokens reappear 2026-03-07 | 4.56M | 0.50M | MIXED ← 5m surging 2026-03-08 | 16.86M | 3.44M | MIXED ← 5m now dominant (83%) 2026-03-10 | 10.55M | 0.51M | MIXED 2026-03-15 | 19.47M | 1.84M | MIXED 2026-03-21 | 21.37M | 1.70M | MIXED ← 93% 5m 2026-03-22 | 13.48M | 2.85M | MIXED ``` The transition is visible to the day: **March 6 is when 5m tokens first reappear** after 33 days of clean 1h-only behavior. By March 8, 5m tokens outnumber 1h by 5:1. This is consistent with a server-side configuration change being rolled out gradually then completing around March 8. --- ## Cost impact Applying official Anthropic pricing (rates.json, updated 2026-04-09): Combined dataset (119,866 API calls, two machines): **claude-sonnet-4-6** (`cache_write_5m = $3.75/MTok`, `cache_write_1h = $6.00/MTok`, `cache_read = $0.30/MTok`): | Month | Calls | Actual cost | Cost with 1h TTL | Overpaid | % waste | |-------|-------|-------------|-----------------|----------|---------| | Jan 2026 | 2,639 | $78.99 | $37.54 | $41.45 | **52.5%** | | Feb 2026 | 27,220 | $1,120.43 | $1,108.11 | $12.32 | **1.1%** ← nearly 0 on 1h | | Mar 2026 | 68,264 | $2,776.11 | $2,057.01 | $719.09 | **25.9%** | | Apr 2026 | 21,743 | $1,193.01 | $1,016.78 | $176.23 | **14.8%** | | **Total** | **119,866** | **$5,561.17** | **$4,612.09** | **$949.08** | **17.1%** | **claude-opus-4-6** (`cache_write_5m = $6.25/MTok`, `cache_write_1h = $10.00/MTok`, `cache_read = $0.50/MTok`): | Month | Calls | Actual cost | Cost with 1h TTL | Overpaid | % waste | |-------|-------|-------------|-----------------|----------|---------| | Jan 2026 | 2,639 | $131.65 | $62.57 | $69.08 | **52.5%** | | Feb 2026 | 27,220 | $1,867.38 | $1,846.85 | $20.53 | **1.1%** ← nearly 0 on 1h | | Mar 2026 | 68,264 | $4,626.84 | $3,428.36 | $1,198.49 | **25.9%** | | Apr 2026 | 21,743 | $1,988.35 | $1,694.64 | $293.71 | **14.8%** | | **Total** | **119,866** | **$9,268.97** | **$7,687.17** | **$1,581.80** | **17.1%** | February — the month Anthropic was defaulting to 1h TTL — shows only **1.1% waste** (trace 5m activity from one machine on one day). Every other month shows 15–53% overpayment from 5m cache re-creations. The cost difference is explained entirely by TTL tier, not by usage volume. The **percentage waste is identical across model tiers** (17.1%) because it is driven purely by the 5m/1h token split, not by per-token price. ### Why 5m TTL is so expensive in practice With 5m TTL, any pause in a session longer than 5 minutes causes the entire cached context to expire. On the next turn, Claude Code must re-upload that context as a fresh `cache_creation` at the write rate, rather than a `cache_read` at the read rate. The write rate is **12.5× more expensive** than the read rate for Sonnet, and the same ratio holds for Opus. For long coding sessions — which are the primary Claude Code use case — this creates a compounding penalty: the longer and more complex your session, the more context you have cached, and the more expensive each cache expiry becomes. Over the 3-month period analyzed: - **220M tokens** were written to the 5m tier - Those same tokens generated **5.7B cache reads** — meaning they were actively being used - Had those 220M tokens been on the 1h tier, re-accesses within the same hour would be reads (~$0.30–0.50/MTok) instead of re-creations (~$3.75–6.25/MTok) --- ## Quota impact Users on Pro/subscription plans are quota-limited, not just cost-limited. Cache creation tokens count toward quota at full rate; cache reads are significantly cheaper (the exact coefficient is under investigation in #45756). The silent reversion to 5m TTL in March is the most likely explanation for why subscription users began hitting their 5-hour quota limits for the first time — including the author of this issue, who had never hit quota limits before March 2026. --- ## Hypothesis The data strongly suggests that **1h TTL was the intended default for Claude Code** and was in place as of early February 2026. Sometime between Feb 27 and Mar 8, 2026, Anthropic silently changed the default to 5m TTL — either intentionally as a cost-saving measure, or accidentally as an infrastructure regression. Evidence supporting "1h was the intended default": - Phase 2 (1h ONLY) shows *zero* 5m tokens across **14 separate active days** spanning 3+ weeks — this is not noise or partial rollout, it is consistent deliberate behavior - The February cost profile is the only month with 0% overpayment — it represents what users should have been paying all along - The March reversion immediately produced the largest 5m-tier days in the entire dataset (30M tokens on Mar 22 alone), suggesting a sudden configuration flip rather than gradual drift - Subscription users began hitting 5-hour quota limits **for the first time** in March — directly coinciding with the reversion The most likely sequence of events: 1. **~Feb 1 and prior**: Anthropic defaulted to 1h TTL for Claude Code subscription users 2. **~Mar 6**: 5m tokens begin reappearing — gradual rollout of the change or partial infrastructure flip 3. **~Mar 8**: 5m TTL becomes dominant — the regression is fully in effect across both tested machines and accounts 4. **Mar 8+**: Mixed behavior continues, suggesting either incomplete rollout, A/B testing, or regional infrastructure variance The 33-day window of clean 1h-only behavior (Feb 1 – Mar 5) across two independent machines and two separate accounts makes this one of the strongest available signals that **1h TTL was Anthropic's deliberate default**, not a fluke. --- ## Request 1. **Confirm or deny** whether Anthropic made a server-side TTL default change in early February 2026 and reverted it in early March 2026 2. **Clarify the intended TTL behavior** for claude-code sessions — is 5m the intended default, or was 1h intended to be permanent? 3. **Consider restoring 1h TTL as the default** for Claude Code sessions, or exposing it as a user-configurable option. The 5m TTL is disproportionately punishing for the long-session, high-context use case that defines Claude Code usage 4. **Disclose quota counting behavior for cache_read tokens** (ref #45756) so users can make informed decisions about their usage patterns --- ## Methodology - Source: raw `~/.claude/projects/**/*.jsonl` session files (Claude Code stores per-message API responses including full `usage` objects) - Extraction: filtered for `type: "assistant"` entries with `message.usage.cache_creation` field - No external tools or proxies involved — this data comes directly from Claude Code's own session logs - Analysis tool: [cnighswonger/claude-code-cache-fix](https://github.com/cnighswonger/claude-code-cache-fix) `quota-analysis --source` mode (added to support this investigation) - Pricing: official Anthropic rates from `rates.json` (updated 2026-04-09)

我来举个很简单的例子吧。克老师的thinking process的纠结程度跟qwen有的一拼 我贴了一张bird 16.23进 22.5出的图给它，然后后面因为已经跌了，schwab的报价是实时的，所以ask mark bid在20.83左右。然后它就是没想到这个代表已经跌了，于是想了一圈又一圈。 /uploads/short-url/fRjNa6AWPAdeLTsTAB2gXcPw92W.jpeg?dl=1 its ok to 想一遍又一遍 但这就是你的token

grok能力有代差只好工程补 grounding里search强度最高的就是grok 所以确实适合做fact check

（我猜）人类学其实也不是单纯的greedy或者evil，他们应该是用户增长太快搞不到算力来支持了，只好压缩订阅用户来保障API用户 包括最近模型降智应该也是降低了reasoning强度强化了quantization之类的

反人类学除了写码别的一般吧。

你把他们想得太好了。

cc知道自己慢所以出了个更贵的opus fast

现在蒸馏都靠中转商了，国内卖代理，用用户输入和Claude输出炼丹

公司用Claude自己嫖codex，是的Claude慢一些。不过我用claude code+gpt 也比codex慢，所以怀疑其实是cc的调用流程问题（或者说其实可能是个feature）

claude pro二十分钟就到limit 用个锤子

为什么不用codex，量大管饱，现在100刀的plan还双倍limit，而且我感觉Claude的数学水平并没有gpt高……

codex用起来总感觉是那种，嘴上吹着牛逼说小问题结果把问题越改越大的人 不过量确实大，而且能白嫖

我用下来还好啊，我反而感觉codex天天喜欢偷懒，不按我写的规范做，就做做表面功夫，比如有个地方要做数学推导他就一定先猜几个乱七八糟的明显有问题的规律，被我骂一通才真的上数学推导

大家有找到方法增加usage limit吗？ 我还买了amazon q，听说用的是同一个模型。

我们公司已经全部从cc订阅转成bedrock的api了

折木奉太郎: 国内卖代理，用用户输入和Claude输出炼丹 这生意模式有点nb。。

你这么说，我感觉我LinkedIn上起码有三个人干这个生意，对外都叫neocloud。

braket: 增加usage limit API，只要银行账户够就管饱 Codex 买 Business 版然后充值 Credit 也是量大管饱。Codex Business 版不需要 seats

我有pro 20刀那个，随随便便一会儿就到limit了。再加一些skills一些artifacts更是秒到。有人试过用公司CC的api干自己的私活吗？这种是不是巨容易被发现？因为使用IP不一样？

抱歉，我忘了说，”如何在尽量省钱的情况下增加limit”。再建一个账号？

走经费报销，申请一些带一点点research funding的小grant

Alila: GLM coding plan 刚刚抢了一次 完全抢不到 而且小红书上刷到很多因为说 翻墙 境外使用 而被封的

认真回答这个问题的话 app - limit消耗快无非就是 1）激活的插件太多 2）模型乱搜索和使用内置工具 3）用了最贵的模型 4）被人类学暗中削弱。缓解办法也是去设置里仔细看一下到底自己激活了哪些额外功能，是否可以一一关掉。 code - 上面的都适用，但是额外的还可以看看本机的.claude/settings.json里的配置。这里面有很多可能导致context浪费或者缓存不命中的晦涩bug。这个可以让claude自己去claude code的github repo搜issue来对比。可以辅助grok的搜推特来交叉验证。 认真audit的话，一般都能找到不少导致用量消耗过快的原因。

千万不要，内容100%被记录

我现在直接windsurf swe1.6，完全免费没有限制，模型一般般，但是能凑合用，毕竟白嫖。别家白嫖都有额度限制。

我最近搞了个qwen code本地量化跑，感觉还行，就是VRAM有限 context比较短

Gemini真有fact check吗，基本上每次问他问题都是一本正经的胡扯。经常我5秒就能谷歌到一个反驳他的事实，还不承认自己的错误。感觉不用其他工具cross check根本没法用。不过胜在学生免费。

我已经在用codex-5.3 high部分代替opus了 个人项目 opus现在只用来plan了 20刀的额度说没就没 sonnet也不用了 用codex mini xhigh代替

Gemini不喜欢上网查证 妥协的方法就是万事deep research

我说的是Chat

pro 订阅不给用 claude code 了

Funk: 用公司CC的api干自己的私活吗 隐私是小事。更大的问题是用公司 API 产出的东西归公司所有。回头影响私活上市，损失单位为上亿

还是codex吧，量大管饱，现在貌似也不错了。

大家都对比的码工，有没有人对比过做文档分析，法律，合规分析和写合同哪家幻觉最少输出最精确和优美？

我只开了20块的claude pro，但是充值了gpt pro。应用物理这方面至少在我的领域推理真是yyds。

开了20 usd pro. 结果 今天早上刚分析了一个dataset, 然后就不允许我继续用了 /uploads/short-url/t4WPPtSVfK1bSdKt4tFS5GuQ6mZ.png?dl=1

最近用 Codex Business，除了每个月 $25，快的时候一天额外用掉 $200。每个月上千是比较正常的

3a0587: 开了20 usd pro claude 20usd 的plan感觉根本没用

好久没有用claude了，今天用了一个小多一点，还没用4.7，用的sonnet 4.6都给用到limit了，现在pro也太拉了吧

最近只用codex

200​才能打 昨晚弄了个盯着跑的任务 周limit75%干到了100% 今天折腾了一天openrouter免费的 简直是一坨 codex team plus 20​读了下project干满了5hr 感觉只能大佬们plan完好 然后小弟们干活了 说实话好东西干活确实快 好 省时间 搞了一天免费model帮倒忙浪费我几小时 以后limit了就给自己放假 不能一直干

用了2天免费claude太慢了，刚换了codex感觉今晚小proj就能好了。

感觉Gemni 是这几个中最弱的

claude真的是最恶心的。模型调的非常爱偷懒，花了一堆token大多数是造假胡编，经常不follow instruction。而且非常花token，有很多耗token的花招。ceo就是个毫无道德感但非常爱装高尚的傻逼。

皇太子都在干这个

巴比，能不能美国的中转站全倒闭了，只能剩我们一家

就是道德婊，4.7比4.6能花多了，有时候光看它在跑的command就知道是在token ms了