[Bug] Excessive token consumption rate - usage depleting faster than expected

[ricardostmalo]

Bug Description

Hi Anthropic/Claude Code team. First, thank you so much for all the amazing work you do :)

I’m a grateful user, but token usage is depleting much faster than expected on Claude Code (v2.1.87, macOS darwin). Full exhaustion in less than an hour vs hours previously. I rapidly consume my 5hr limit. It feels concerning and doesn’t match prior behavior.

Thank you.

Environment Info

• Platform: darwin
• Terminal: ghostty
• Version: 2.1.87
• Feedback ID: aed9f663-d93c-47f1-bb7d-d70affbf6d61

Errors

[]

[github-actions]

Found 3 possible duplicate issues:

1. Excessive token consumption - 70% usage within one hour of normal use #41200
2. Abnormal token consumption rate on Opus 4.5 — 100% usage in ~1 hour #39966
3. [Bug] Excessive token consumption rate with two Claude Code CLI instances #41145

This issue will be automatically closed as a duplicate in 3 days.

• If your issue is a duplicate, please close it and 👍 the existing issue instead
• To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

[Verbludoed]

About ten days ago, when everything still worked normally, even the Free plan would give 1–2 hour sessions in agent mode via MCP, using Sonnet 4.6 with extended thinking. At that time, weekly usage quota would be fully exhausted within two days (during off-peak hours).
Now, a Sonnet session (without extended thinking) terminates after just ONE request with 3–4 tool calls — yet weekly quota limit does NOT run out.
This suggests that sessions are not being terminated by actual token-limit exhaustion, but by something else. In other words, this is likely a bug, not a new policy from management that's suddenly become greedy.
I really hope that's the case. Maybe they'll actually fix it... :(

[Verbludoed]

Came to think of it: maybe the issue isn't the token quota, but the rate limit — i.e., requests-per-minute throttling. Not just slowing down, but hard-cutting without explanation (jerks).
Just tested: turned out both limits are in play.
Short version: made requests strictly one tool call per turn. Managed 27 (!!!) elementary requests total. Session exhausted in ~30 minutes — but at least it showed the infamous 90% token-quota depletion. Still off-peak hour. Sonnet 4.6, no extended thinking.
This is, of course, much better than instant exhaustion after one request — but still a sad fraction compared to what worked 10 days ago. And this looks less like a bug, and more like capitalism baring its teeth.
That's about it, I guess... :((

[drewAnderson-val]

also experiencing the same issue

[bmajkut]

Same issue on my side, I am using 110 EUR plan and Today even starting the conversation with simple question costs me around 3% of my tokens.