Seeking Help with Claude-3-Haiku API Quota Issues

Google Cloud Build with AI Custom ML & MLOps
1

Hello everyone,

I’m encountering a persistent issue with the Claude-3-haiku API. Despite having a quota of 10 requests per minute, I’m frequently receiving the following error message:

[
    {
        "error": {
            "code": 429,
            "message": "Quota exceeded for aiplatform.googleapis.com/online_prediction_tokens_per_minute_per_base_model with base model: anthropic-claude-3-haiku. Please submit a quota increase request. https://cloud.google.com/vertex-ai/docs/generative-ai/quotas-genai.",
            "status": "RESOURCE_EXHAUSTED"
        }
    }
]

This error indicates that I’ve exceeded the quota, but according to my current configuration, I should be able to make 10 requests per minute. I even applied for and received an upgrade to 20 requests per minute, but the issue persists.

xukecheng_0-1718274642383.png

Does anyone have any insights or suggestions on how to resolve this? Any help would be greatly appreciated.

5 Likes