Cursor (AI IDE)$ explicithighCluster of 10 signals
Card #483 · Cursor (AI IDE)

Excessive and non-transparent token consumption in newer models

We are experiencing a dramatic and unexplained increase in token usage, particularly with the 5.5 and Composer 2.5 versions. The consumption feels abnormal and non-transparent, often exhausting monthly budgets or daily limits in a fraction of the usual time.

Cursor (AI IDE)Updated 28d ago0.26
Pain score
0.26/ 1.00 · weighted product of four components
Reach0.70
distinct authors (log-normalized)
Recency1.00
freshness decay, half-life months
Engagement1.00
upvotes + comments, normalized
Monetization1.00
willingness-to-pay cues in evidence
§ Evidence — 6 verified quotes
I’ve noticed a dramatic increase in my token consumption.
Forum·@samlinux··source ↗
Our token usage has gone up 5 fold with 5.5.
Forum·@dpupek··source ↗
I consume all my token in 15 minutes with 1-2 task using my chatGPT authentification.
Forum·@mathieu.lefrancois··source ↗
Codex 5.5 is consuming tokens as if its drinking gasoline even at thinking medium
Forum·@Dakshk··source ↗
the change from 5.2 to 5.5 is dramatic.
Forum·@Marius91··source ↗
My dashboard suggests that when using codex I used 95 Million tokens input, 25 Million cached input to produce 600K output tokens!!??
Forum·@kurlytail··source ↗

Comments are a Pro feature — join the conversation, share what you've shipped, hear what others are building.

Upgrade to Pro