[BUG] Abnormal rate limit consumption — 1-2 prompts exhausting 5-hour window

[eburgagni89]

Preflight Checklist

• I have searched existing issues and this hasn't been reported yet
• This is a single bug report (please file separate reports for different bugs)
• I am using the latest version of Claude Code

What's Wrong?

Starting around March 23-24, 2026, my 5-hour rate limit is being exhausted
after only 1-2 prompts/interactions. Previously I could have extended sessions
with dozens of interactions before hitting limits.

Environment:

• Claude Code version: 2.1.79 (VS Code extension)
• Model: claude-opus-4-6[1m] (1M context)
• Plan: [5x]
• Platform: macOS Darwin 24.6.0

Reproduction:

1. Start a new conversation
2. Send 1-2 prompts (even simple ones)
3. Rate limit hit with "resets at X PM" message

Expected: Dozens of interactions before hitting the 5-hour limit
Actual: 1-2 interactions consume the entire limit

This appears to be a widespread issue — multiple users across platforms
are reporting the same behavior around the same timeframe.

Additional context:

• Using subagents (Agent tool) for parallel work — these may be
  consuming disproportionate rate limit tokens
• Long conversation context (1M window) may be contributing
• The issue started suddenly, not gradually

What Should Happen?

Rate limits should not be hit after a few prompts. This is abnormal for a tier that cost $100/month

Error Messages/Logs

Steps to Reproduce

Use claude code extension in VS studio. Submit a few prompts. Watch usage spike abnormally and then get locked out for 5 hours until the reset happens.

Claude Model

Opus

Is this a regression?

I don't know

Last Working Version

No response

Claude Code Version

2.1.79 (VS Code extension)

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

No response

[yuu-takigawa]

I encountered the same problem; I used up my 5-hour limit on the Max 5X Plan after only two rounds of conversations. It's unbelievable.

[moonipulate]

Same issue here. Does it have anything to do with CLI version or model related?

[sophiaashi]

1-2 prompts exhausting the limit sounds like the cache_creation bug others have reported in #38350. The token accounting seems broken.

While waiting for a fix, multi-model routing helped me — send the simple stuff through GPT-4o/Gemini so your Anthropic quota lasts the full session. I went from hitting limits daily to not hitting them at all.

Setup and details here if useful: https://dev.to/sophiaashi/claude-code-rate-limit-on-max-plan-the-workaround-developers-are-actually-using-in-2026-16g2

We also have a Discord for people dealing with this: https://discord.gg/tvAtTj2zHv