Pro Max 5x quota exhausted in 1.5 hours despite moderate usage

Post by bcherny » Sun, Apr 12, 2026, 3:15 PM UTC

rawicki wrote: post #231

bcherny wrote: post #210

Hey all, Boris from the Claude Code team here. We've been investigating these reports, and a few of the top issues we've found are: 1. Prompt cache misses when using 1M token context window are expensive. Since Claude Code uses a 1 hour prompt cache window for the main agent, if you leave your computer for over an hour then continue a stale session, it's often a full cache miss. To improve this, we have shipped a few…

For me definitely the worst regression was the system prompt telling claude to analyze file to check if it's malware at every read. That correlates with me seeing also early exhausted quotas and acknowledgments of "not a malware" at almost every step. It is a horrible error of judgement to insert a complex request for such a basic ability. It is also an error of judgement to make claude make decisions whether it want…

Post by bcherny » Sun, Apr 12, 2026, 3:15 PM UTC

brokencode wrote: post #239

bcherny wrote: post #210

Hey all, Boris from the Claude Code team here. We've been investigating these reports, and a few of the top issues we've found are: 1. Prompt cache misses when using 1M token context window are expensive. Since Claude Code uses a 1 hour prompt cache window for the main agent, if you leave your computer for over an hour then continue a stale session, it's often a full cache miss. To improve this, we have shipped a few…

Would it be possible to increase the cache duration if misses are a frequent source of problems? Maybe using a heartbeat to detect live sessions to cache longer than sessions the user has already closed. And only do it for long sessions where a cache miss would be very expensive.

Post by losvedir » Sun, Apr 12, 2026, 3:16 PM UTC

SkyPuncher wrote: post #125

I skimmed the issue. No wonder Anthropic closes these tickets out without much action. That’s just a wall of AI garbage. Here’s what I’ve done to mostly fix my usage issues: * Turn on max thinking on every session. It save tokens overall because I’m not correcting it of having it waste energy on dead paths. * keep active sessions active. It seems like caches are expiring after ~5 minutes (especially during peak usage…

Post by rawicki » Sun, Apr 12, 2026, 3:17 PM UTC

bcherny wrote: post #241

rawicki wrote: post #231

Earlier quoted context omitted.

For me definitely the worst regression was the system prompt telling claude to analyze file to check if it's malware at every read. That correlates with me seeing also early exhausted quotas and acknowledgments of "not a malware" at almost every step. It is a horrible error of judgement to insert a complex request for such a basic ability. It is also an error of judgement to make claude make decisions whether it want…

I don't think that's accurate. The malware prompt has been around since Sonnet 3.7. We carefully evaled it for each new model release and found no regression to intelligence, alongside improved scores for cyber risk. That said, we have removed the prompt for Opus 4.6 since it no longer needed it.

Post by yummytummy » Sun, Apr 12, 2026, 3:17 PM UTC

bcherny wrote: post #210

Hey all, Boris from the Claude Code team here. We've been investigating these reports, and a few of the top issues we've found are: 1. Prompt cache misses when using 1M token context window are expensive. Since Claude Code uses a 1 hour prompt cache window for the main agent, if you leave your computer for over an hour then continue a stale session, it's often a full cache miss. To improve this, we have shipped a few…