Hi team,
Our project was upgraded to Tier 2, but the API still enforces the Tier 1 daily request quota on the TTS models.
Project: Default Gemini Project (gen-lang-client-022828…)
Billing: Tier 2 · Prepay (shown in AI Studio → API Keys since 2026-10-04)
Models: gemini-3.8-flash-lite-tts, gemini-3.8-flash-tts
AI Studio → Rate Limit shows 1K RPM / 100K TPM / 10K RPD for both models. However, generateContent and streamGenerateContent keep returning 429 RESOURCE_EXHAUSTED once we pass 100 requests per day:
QuotaFailure: quotaId “GenerateRequestsPerDayPerProjectPerModel”,
quotaMetric “generativelanguage.googleapis.com/generate_requests_per_model_per_day”,
quotaDimensions { model: “gemini-3.8-flash-lite-tts”, location: “global” },
quotaValue “100”
The same happens for gemini-3.8-flash-tts. The most recent occurrence was 2026-10-05 05:22 UTC, about 16 hours after Tier 2 appeared in AI Studio. The project has a single API key, so it is not a different project.
This is a production app (voice replies of a fitness coach). Every day after ~100 requests our users are switched to a slower fallback. Could you please apply the Tier 2 quotas to this project, or tell us what else we need to do?
Thank you!