claude ai spending limit gets ignored #7980

Open
opened 2026-02-16 18:08:50 -05:00 by yindo · 3 comments
Owner

Originally created by @Flewrider on GitHub (Jan 29, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

So i have been using claude opus 4.5 via opencode. I have an extended spending limit set on the claude page its set to 5€. But it literally just ignored that and continued working an now I have spend 43€. don't really know if thats a claude issue or a opencode issue.

Plugins

No response

OpenCode version

No response

Steps to reproduce

Set spending limit.
use claude models

Screenshot and/or share link

Image

Operating System

Windows 11

Terminal

Windows Terminal

Originally created by @Flewrider on GitHub (Jan 29, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description So i have been using claude opus 4.5 via opencode. I have an extended spending limit set on the claude page its set to 5€. But it literally just ignored that and continued working an now I have spend 43€. don't really know if thats a claude issue or a opencode issue. ### Plugins _No response_ ### OpenCode version _No response_ ### Steps to reproduce Set spending limit. use claude models ### Screenshot and/or share link <img width="922" height="311" alt="Image" src="https://github.com/user-attachments/assets/a5d3eca7-dc5d-40bf-a3a2-e361e10b202c" /> ### Operating System Windows 11 ### Terminal Windows Terminal
yindo added the bug label 2026-02-16 18:08:50 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Jan 29, 2026):

This issue might be a duplicate of existing issues. Please check:

  • #8945: Mismatch between token spent and billing - spending limit was set to $14 but limit was reached despite lower estimated usage
  • #11170: Billing Issue - user reports being overcharged significantly (charged ~10x the expected amount for Qwen3 Coder)
  • #7767: Session cost under-reported for sessions with 100+ messages - cost calculation only shows last ~100 messages
  • #7387: Multi Model Cost Calculations are Bugged - cost calculation decreases when switching models mid-session
  • #6989: Spent amount in context randomly decreases after request - display of spent value is unreliable
  • #11027: Cost of session doesn't include cost of subagents - incomplete cost tracking
  • #8234: Excessive token consumption since Jan 12, 2026 - entire project context sent on every request causing unexpected charges
  • #5951: Token count is way off - massive mismatch between UI display (85k tokens) and actual API consumption (3.55M tokens)
  • #10272: Hidden calls to Claude Haiku - unexpected hidden API calls being billed without user knowledge

Feel free to ignore if none of these address your specific case.

@github-actions[bot] commented on GitHub (Jan 29, 2026): This issue might be a duplicate of existing issues. Please check: - #8945: Mismatch between token spent and billing - spending limit was set to $14 but limit was reached despite lower estimated usage - #11170: Billing Issue - user reports being overcharged significantly (charged ~10x the expected amount for Qwen3 Coder) - #7767: Session cost under-reported for sessions with 100+ messages - cost calculation only shows last ~100 messages - #7387: Multi Model Cost Calculations are Bugged - cost calculation decreases when switching models mid-session - #6989: Spent amount in context randomly decreases after request - display of spent value is unreliable - #11027: Cost of session doesn't include cost of subagents - incomplete cost tracking - #8234: Excessive token consumption since Jan 12, 2026 - entire project context sent on every request causing unexpected charges - #5951: Token count is way off - massive mismatch between UI display (85k tokens) and actual API consumption (3.55M tokens) - #10272: Hidden calls to Claude Haiku - unexpected hidden API calls being billed without user knowledge Feel free to ignore if none of these address your specific case.
Author
Owner

@rekram1-node commented on GitHub (Jan 29, 2026):

Spending limit stuff should be enforced by their api I'd imagine, not us

@rekram1-node commented on GitHub (Jan 29, 2026): Spending limit stuff should be enforced by their api I'd imagine, not us
Author
Owner

@Flewrider commented on GitHub (Jan 29, 2026):

Well it is working in claude code so thats why i thought this could be an opencode issue

@Flewrider commented on GitHub (Jan 29, 2026): Well it is working in claude code so thats why i thought this could be an opencode issue
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#7980