Curious on what each token type is? Also curious if we know anything about the cost of each type and while not knowing the limits, if certain tokens use up that limit further and by how much? As far as my understanding goes: Input: Prompt Output: The.. output on the llm Write Cache: Writing to …

@Reznal Input tokens: request, attached files, rules, docs, read files, MCP output … Output tokens: Chat text, Code, data sent to MCP from AI,… Write Cache: previous chat messages/context to be saved for the session Read cache: reading cache without having to fetch data from users computer, basica…

Thats for the details :slight_smile: Getting an api cost for each in each model would be amazing. Although most of my prompts that have any size majority of the tokens are Read Cache and I still get rate limited nearly instantly.

Yeah, there is a feature request for this and I forwarded it to Cursor Team.

Okay its fine that Read Cache is the cheapest of all, but if it goes bezerk on the amont it might still be a issue. Have a look at this log token-based usage calls to claude-4-sonnet, totalling: $2.62. Input tokens: 1120, Output tokens: 10751, Cache write tokens: 117388, Cache read tokens: 5252615 …

@gram12321 is this from a long chat?

Different token types

Discussions

Topic		Replies	Views
This is getting out of hand Feedback	12	1512	August 8, 2025
Understanding LLM Token Usage Guides	0	19920	July 20, 2025
How is the Claude-4-sonnet consumption record calculated Help	6	772	July 9, 2025
How do cache reads and writes works? Discussions	1	4799	August 17, 2025
Why cache read per request can exceed model context window in token usage envent Help context	1	55	April 27, 2026

Different token types

Related topics