Gemini Context Caching Broken on Paid Tier 1 Account — max_total_token_count=0
Hi everyone,
I’m hitting a provisioning issue with Gemini context caching and hoping someone from the Google team or the community can point me in the right direction.
The error:
400 INVALID_ARGUMENT: Cached content is too large.
total_token_count=1616899, max_total_token_count=0
What’s happening:
My account is on Paid Tier 1 with active billing confirmed. Despite this, the context caching API is treating my cache quota as 0 — rejecting any cache creation that exceeds a small token threshold. Caching 1-2 video chunks succeeds. Caching 3+ chunks fails with the error above.
What my Console shows:
- Paid Tier quota: Unlimited
- Free Tier quota: 0
- My account is being treated as Free Tier despite active paid billing
What I’ve already tried:
- Removed the quota override in IAM → Quotas & System Limits twice — did not resolve it
- The issue appears to be a misclassification in the backend provisioning system, not something surfaced in the Console UI
Project ID: gen-lang-client-0174334843
This seems to be a known issue where paid accounts don’t get their tier classification resynced properly after upgrading. I’m not looking for a quota increase — the paid tier limit is already set to Unlimited. The account just needs to be resynced so the caching API reflects the correct tier.
Has anyone else run into this? Is there a Google team member who can look into the provisioning on this project? Any help appreciated.