01github.com
Pro Max 5x Quota Exhausted in 1.5 Hours Despite Moderate Usage
Users report that Claude Code on a Pro Max 5x plan experiences rapid quota exhaustion, likely because cache_read tokens count at full rate against rate limits rather than at a reduced 1/10 rate. Background sessions and automatic context compaction further amplify token consumption, making the 1M context window unsustainable under current rate-limiting logic.