[BUG] Despite being paid for extra usages still receiving API Error: 400: type":"invalid_request_error","message":"You're out of extra usage. Add more at claude.ai/settings/usage and keep going.

Resolved 💬 5 comments Opened Apr 8, 2026 by tushitdave Closed Apr 8, 2026

Preflight Checklist

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

What's Wrong?

Got it — this is important context, and honestly, your suspicion is valid. The screenshot clearly shows extra usage already exceeded + auto-reload ON, yet the API is still blocking you. That strengthens your case.

Here’s a stronger, more assertive GitHub issue message incorporating this:

---

🐛 Issue: API Blocking Requests Despite Extra Usage Enabled & Paid

Hi Team,

I’m encountering the following error while using the Claude API:

API Error: 400 
{
  "type": "error",
  "error": {
    "type": "invalid_request_error",
    "message": "You're out of extra usage. Add more at claude.ai/settings/usage and keep going."
  },
  "request_id": "req_011CZqnb9kHEjoyRX6EAR4mn"
}

---

🔍 Observed Behavior

  • The API is rejecting requests stating that I’m “out of extra usage.”
  • However, based on my account settings:
  • Extra usage is already enabled (toggle ON)
  • Monthly spend limit is set
  • Amount has already been charged ($20.22 spent)
  • Usage shows 101% consumed under extra usage
  • Auto-reload is enabled

---

⚠️ Concern

Despite:

  • Paying for extra usage
  • Enabling extra usage toggle
  • Having auto-reload active

…the API is still blocking requests instead of continuing usage.

This creates a hard failure in production workflows, which should ideally not happen when billing is configured correctly.

---

❓ Questions

  1. Why is the API still blocking requests even though extra usage is enabled and billing is active?
  2. Is there a delay or sync issue between billing and API quota enforcement?
  3. Does exceeding 100% (e.g., 101%) require manual intervention despite auto-reload being enabled?
  4. Are there hidden caps or throttling rules not reflected in the UI?

---

🧪 Additional Details

  • Request ID: req_011CZqnb9kHEjoyRX6EAR4mn
  • Occurrence: [Consistent / Intermittent — update this]
  • Usage Page Screenshot: (attached)
  • Environment: [Add SDK / API usage details]

---

🚨 Impact

This issue is blocking API usage even after payment and proper configuration, which impacts reliability for production use cases.

---

🙏 Request

Please investigate this inconsistency between billing and API enforcement and advise on:

  • Immediate resolution
  • Correct configuration (if anything is missing)
  • Expected behavior when extra usage exceeds 100%

Other details

Version: 2.1.25
Session name: /rename to add a name
Session ID: 119da7f7-6542-4bd8-af1e-a7f973005ed5
Login method: Claude Pro Account
Organization: tushitdavergtu@gmail.com's Organization
Email: tushitdavergtu@gmail.com

Model: sonnet (claude-sonnet-4-5-20250929)
IDE: Installed VS Code extension
MCP servers: claude.ai Google Calendar △, claude.ai Gmail △
Memory: project (CLAUDE.md)
Setting sources: User settings, Project local settings

<img width="1235" height="768" alt="Image" src="https://github.com/user-attachments/assets/c0afca5f-ff96-4bd1-b2ba-a627aaac8da4" />

What Should Happen?

When already paid what is blocking API to get it started,
Below error should have been removed:-
API Error: 400 {"type":"error","error":{"type":"invalid_request_error","message":"You're out of extra usage. Add more at claude.ai/settings/usage and keep
going."},"request_id":"req_011CZqnb9kHEjoyRX6EAR4mn"}

Error Messages/Logs

Steps to Reproduce

None

Claude Model

Sonnet (default)

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.25

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

VS Code integrated terminal

Additional Information

_No response_

View original on GitHub ↗

This issue has 5 comments on GitHub. Read the full discussion on GitHub ↗