I get 'You exceeded your current quota' even though I have 84% context left on Pro Plan.
What happened?
I get 'You exceeded your current quota' even though I have 84% context left. I also got this from the beginning using Gemini-cli. I'm stuck now on a paied pro plan. I got this after upgrading last 2 releases.
What did you expect to happen?
I would like to use Gemini-CLI.
Client information
- CLI Version: 0.5.4
- Git Commit: f3cb841e
- Session ID: 7bab6266-ed86-41cc-a123-5dbcb569b559
- Operating System: darwin v24.8.0
- Sandbox Environment: no sandbox
- Model Version: gemini-2.5-pro
- Memory Usage: 441.3 MB
Login information
I use: export GEMINI_API_KEY=xxx in my .zshrc I have tried switching /auth with Google account and back. Same problem.
Anything else we need to know?
This is the error:
✕ [API Error: {"error":{"message":"{\n "error": {\n "code": 429,\n "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.\n* Quota exceeded for metric:
generativelanguage.googleapis.com/generate_content_free_tier_input_token_count, limit: 125000\nPlease retry in 15.002899939s.",\n
"status": "RESOURCE_EXHAUSTED",\n "details": [\n {\n "@type": "type.googleapis.com/google.rpc.QuotaFailure",\n
"violations": [\n {\n "quotaMetric":
"generativelanguage.googleapis.com/generate_content_free_tier_input_token_count",\n "quotaId":
"GenerateContentInputTokensPerModelPerMinute-FreeTier",\n "quotaDimensions": {\n "location":
"global",\n "model": "gemini-2.5-pro"\n },\n "quotaValue": "125000"\n }\n
]\n },\n {\n "@type": "type.googleapis.com/google.rpc.Help",\n "links": [\n {\n
"description": "Learn more about Gemini API quotas",\n "url": "https://ai.google.dev/gemini-api/docs/rate-limits"\n
}\n ]\n },\n {\n "@type": "type.googleapis.com/google.rpc.RetryInfo",\n "retryDelay":
"15s"\n }\n ]\n }\n}\n","code":429,"status":"Too Many Requests"}}]
Please wait and try again later. To increase your limits, request a quota increase through AI Studio, or switch to another /auth method