URGENT: Huge cost cache increase issue

[junkx]

Hi,

Its not only a cache issue, its also Gemini flash 3 preview, 3.1 flash lite preview -and maybe more- using x4/x5 MORE OUTPUT TEXT tokens overnight. I didn’t touch any code or any prompt, same amount of call, same json output size.

Other devs are reporting here:

URGENT: The cost of API access has increased since March 16-17, 2026

Hello, Since March 16–17, 2026, I have noticed a significant increase in the costs for API calls using the gemini-3-flash-preview model. We do not use the caching system or the Google search system. Our cost calculations (in terms of user credits UCR) based on the tokens (promptTokenCount, thoughtsTokenCount, and candidatesTokenCount) no longer match the associated costs displayed in Google AI Studio since March 16–17, 2026. The number of requests is valid and has not changed. Before March 16…

/

please confirm if you are signed in using your individual primary accounts or if you are accessing the API through a static or shared credential

I don’t know what that means. Im a solo developper with a basic Google cloud account. I created a project, then linked it in Google Ai studio, where i got my API key.