Error 429 when using Vertex AI API, even though my usage is below quota

[cr3]

I just started implementing claude-3-7-sonnet@20250219 for my app, already getting 429 errors in my development environment. I tried using it in both us-east5 and europe-west1.

The quota page says I'm below the limit, but still getting these.

[caryna]

Hi @cr3,

Welcome to Google Cloud Community!

You are using a type of Claude model (claude-3-7-sonnet@20250219 ), which has a usage limit based on queries per minute (QPM) and tokens per minute (TPM) both input and output tokens.

This will depend on your account and for each region you specified. Try to review your project's quotas on the Quotas & Systems Limits page in the Google Cloud console. You may also consider the solution outlined in the Error Code 429 documentation, as it could provide insights specific to your case scenario.

If the issue persists, please contact Google Cloud Support. When reaching out, include detailed information and relevant screenshots of the errors you’ve encountered. This will assist them in diagnosing and resolving your issue more efficiently.

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.