Just boosted my sub to Ultra mode, because I want to drive fast, not be the “mechanic” in the car and race driver analogy – what I noticed on two relatively short horizon requests it fed Claudey 1m tokens, you can see the previous ones on my older limited Pro account they were all around 150k tokens…

The longer a chat grows, the more the cache read tokens will grow. E.g. if there are 100k tokens in the chat context, and it makes 10 tool calls, then thats at least 1 million cache read tokens. Cache read tokens are 10x cheaper than the input tokens though

has to be a bug. that token usage is not even close to reasonable

The token count here should be correct; the count here includes cached read tokens, which get included based on all prior input tokens at every tool call. Cached input tokens are 10x cheaper than input tokens. If you hover over the token count, it should give you a breakdown by token type.

[Screenshot 2025-07-16 at 2.12.14 AM] you’re right. shame that this means 1 prompt was supposed to cost $3.40.

The unknown text is a bug; we’ll get that fixed.

can’t say that was the part that concerned me, but appreciate it :rofl:

Na token usage has suddenly got pretty wild….. [image] This is on the same chat, but it was ticking along at 40-50k and then suddenly jumping into the multi millions!??

I feel like this needs to be much more clearly documented. This isthe first response that I see that clearly illustrates what’s happening. You may want to write this in the trending thread where people were asking questions regarding how this happens. Link to thread in question: Frustrated with Cur…

When not using MAX mode, Cursor should intelligently build the final prompt to the AI in a more economic way, which should mean the requests are somewhat uniform in size and therefore are more predictable in their usage! With MAX enabled, Cursor will quite happily fill the model’s context window wh…

how to disable cached tokens? I want to work the old fashioned way, like March 1st! Maybe you need money, but I also need my money and don’t need your cached tokens.

Massive token increase on Ultra?

Discussions

cocode (Babak Bandpey) July 16, 2025, 12:36pm 15

very interesting observation.

Pricing Megathread and Q&A

Topic		Replies	Views
Monthly token limit in the $20 Pro Plan for Cursor usage Help	18	26867	January 24, 2026
Extreme token usage Feedback	78	4436	November 9, 2025
For users spending $1,000-2,000/month on usage, is Ultra worth it over Pro + usage-based pricing? Discussions	9	2621	March 15, 2026
Cursor still great, but just got a lot more expensive Discussions	21	8003	August 24, 2025
"Hi” Message Used 13K+ Tokens – Why Is Token Usage So High? Help auto-mode , context	8	606	March 5, 2026

Massive token increase on Ultra?

Related topics