Hi,
Yesterday I noticed that all new batch prediction jobs started failing with this error:
429 The following quota metrics exceed quota limits: aiplatform.googleapis.com/gemini_pro_concurrent_batch_prediction_jobs
Pls assist.
Hi @ank1,
Welcome to Google Cloud Community!
Upon checking, there’s an existing internal case similar to this, and it has already been mitigated. Additionally, I found a similar case for your reference.
You may retry and confirm whether it’s working on your end now.
If it still doesn’t work, regarding the error that you received, if the number of your requests exceeds the capacity allocated to process requests, then error code 429 will be returned. You may check this page for guidance on how to rectify this issue.
In addition, according to this documentation, Gemini 1.5 Pro supports Dynamic Shared Quota (DSQ) which eliminates the need to set quota limits and to submit quota increase requests (QIRs). If you need higher throughput, consider Google’s Provisioned Throughput. Note that it is currently in Preview and access must be requested.
Was this helpful? If so, please accept this answer as “Solution”. If you need additional assistance, reply here within 2 business days and I’ll be happy to help.