Cursor User Burns $378 in One Night as Claude API Calls Blow Past $200 Ultra Plan
lxfater · x · 2026-10-14
Developer lxfater shared a Cursor billing screenshot: despite the $200/month Ultra plan, the Other Models quota hit 100% and on-demand spend reached $378.04 of a $400 cap in a single night, driven by Claude API calls inside Cursor. Cursor's in-house models (Grok, Composer) used only 28% of their quota. The post highlights how third-party model usage auto-converts to on-demand billing once included limits run out — an easy way for heavy users to rack up surprise charges.
More from coding & agent
- Dev argues there's zero reason to use Python in 2026 now that agents write the code — zack_overflow · 2026-10-14
- Giving agents the ability to verify their own work kills 75% of AI coding issues — DanielLockyer · 2026-10-14
- What Should Unattended Agent Runs Log? A Developer Shares an Auditable Design — bulutarkan · 2026-10-14
- RUC's Agent-Reflex trains reflective agents in three stages, scoring 58.6 on long-horizon tool-use benchmarks — RUC-NLPIR · 2026-10-14
- Agent makes 20-25 API calls per run, burning $2,500 — which data APIs hold up? — __KillJoy · 2026-10-14
- Dev rebuilds personal AI call assistant on Executors V2 with Vapi integration — ethanniser · 2026-10-14