URGENT: Huge cost cache increase issue

[junkx]

After 8 days, still no fix from Google; hopefully the engineers are working on resolving the issue and we’ll get refunds + free credits.

Another dev is reporting the issue:

Gemini-3-flash-preview: billing ~50× higher than expected — hidden thinking tokens not reported by deprecated SDK

Single multimodal call (JPEG + short prompt), google.generativeai v0.8.6, zero config: prompt_token_count = 1,107 candidates_token_count = 1,193 total_token_count = 4,598 → hidden gap = 2,298 tokens (not exposed in SDK) With longer prompts, the gap grows to 5,800–15,000 tokens/call. One call produced zero visible output but 6,109 hidden tokens. Billing check: balance before = $8.77, after one call = ~$8.82. Delta ~$0.05 for a call that should cost ~$0.001 based on visible t…