So, im using gemini api for a game that uses generative language api, and I’ve run into a error that seems to imply the tpm for free tier is half as much as listed on the rate limit page? Anyone know something about that?
Heres the error message:
An unexpected error occurred during Gemini API call: 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.’, ‘status’: ‘RESOURCE_EXHAUSTED’, ‘details’: [{‘@type’: ‘type.googleapis.comgoogle.rpc.QuotaFailure’, ‘violations’: [{‘quotaMetric’: ‘generativelanguage.googleapis.com/generate_content_free_tier_input_token_count’, ‘quotaId’: ‘GenerateContentInputTokensPerModelPerMinute-FreeTier’, ‘quotaDimensions’: {‘model’: ‘gemini-2.5-pro’, ‘location’: ‘global’}, ‘quotaValue’: ‘125000’}]}
Hi @Adam_Dobry,
Welcome to the Forum,
Thank you for bringing this to our attention and for providing the detailed error message. We appreciate you taking the time to flag this discrepancy.
After an internal review, we can confirm that the current effective rate limit for tokens per minute (TPM) on the Gemini API free tier is indeed 125,000. The higher number present in our documentation was an error.
We have filed a bug to have the official documentation corrected to reflect the actual limit.
Thank you!
Alright, thanks for clarifying.
Was it really that expensive they had to cut it in half anyway…