Gemini 503 APIError: 503 UNAVAILABLE and Gemini quota exceeded: 429 RESOURCE_EXHAUSTED

Gemini API
, , ,
1

I have been experiencing several errors lately with both Gemini 2.5 pro and flash models which make it IMPOSSIBLE to use my product.

  1. Gemini quota exceeded: 429 RESOURCE_EXHAUSTED. {‘error’: {‘code’: 429, ‘message’: ‘You exceeded your current quota, please check your plan and billing details. For more information on this error, head to: https://ai.google.dev/gemini-api/docs/rate-limits. To monitor your current usage, head to: https://ai.dev/usage?tab=rate-limit. \n* Quota exceeded for metric: generativelanguage.googleapis.com/generate_content_free_tier_requests, limit: 2, model: gemini-2.5-pro\nPlease retry in 39.163101425s.’, ‘status’: ‘RESOURCE_EXHAUSTED’, ‘details’: [{‘@type’: ‘type.googleapis.com/google.rpc.Help’, ‘links’: [{‘description’: ‘Learn more about Gemini API quotas’, ‘url’: ‘https://ai.google.dev/gemini-api/docs/rate-limits’}]}, {‘@type’: ‘type.googleapis.com/google.rpc.QuotaFailure’, ‘violations’: [{‘quotaMetric’: ‘generativelanguage.googleapis.com/generate_content_free_tier_requests’, ‘quotaId’: ‘GenerateRequestsPerMinutePerProjectPerModel-FreeTier’, ‘quotaDimensions’: {‘location’: ‘global’, ‘model’: ‘gemini-2.5-pro’}, ‘quotaValue’: ‘2’}]}, {‘@type’: ‘type.googleapis.com/google.rpc.RetryInfo’, ‘retryDelay’: ‘39s’}]}}"}

  2. Gemini 503 APIError: 503 UNAVAILABLE. {‘error’: {‘code’: 503, ‘message’: ‘The model is overloaded. Please try again later.’, ‘status’: ‘UNAVAILABLE’}}; retrying with adaptive plan"}

I am on paid tier 1 and based on the dashboard data my peak requests are way below the limits. This is very frustrating and I have no idea what else can be done to fix this issue, since my python script already contains multiple fallback scenarios. It has just stopped working the way it used to a few days ago.

Need help urgently!

3

Hi @AIAlert
Based on the error message , it appears you are encountering free_tier quota violations. Could you please confirm your current subscription status and ensure that the API Key you are using is properly linked to a Cloud Project with active billing?
Can you also share screenshots of the dashboard which shows your request usage ?
Thanks