Error as shown in TypingMind chat:
Sorry, the provider of this model has rejected your request (Message: Resource has been exhausted (e.g. check quota).). Please try again or contact support.
Description of Issue:
I am receiving a persistent **“Resource has been exhausted (e.g. check quota)”**error when making requests to the model, despite being well within my plan limits. I use Gemini 3.1 pro.
Troubleshooting Steps Already Taken:
- Checked Quotas: I have verified my current quota metrics, and they do not show that any limits have been breached.
- Rotated API Keys: I generated a brand new API key to rule out a localized key restriction, but the issue persists with the new key.
- Verified Account Tier & Billing: My account is explicitly on the Tier 1 postpaid billing tier (unlimited access to 3.1 pro tier).
- Checked Budget Caps: I have verified that I have not hit any custom set budget or spending limits on the billing account.
Given that my account has standard Tier 1 postpaid access and is completely clear of budget caps, this “quota exhausted” block appears to be a systemic or backend miscalculation. Could you please look into why this error is triggering on my active account