跳至內容

Can not increate invokeModel request to Claude 3.5 Sonnet v2

0

I can not increase quatas in Amazon Bedrock for model Claude 3.5 Sonnet v2. The checkbox labels are not available. And there is a value 'not adjustable' Enter image description here

I need limit as on image bottom Enter image description here

What i need to able to change these quotas? And how to chat AWS Support directly to increase these quatas, i need more throughput performance, cause we developing ai chat assistants?

已提問 2 年前檢視次數 441 次

2 個答案
0

The situation you're describing is common for Amazon Bedrock quotas, especially for models like Claude 3.5 Sonnet v2. The "not adjustable" label and unavailable checkboxes indicate that these quotas cannot be increased through the standard Service Quotas console process.

To increase your quotas for on-demand InvokeModel requests and other Bedrock API-related limits, you'll need to follow a different approach:

  1. Contact AWS Support directly. You can do this by visiting the AWS Support Center at https://support.console.aws.amazon.com/support/home#/

  2. When creating a support case, select the appropriate category related to Amazon Bedrock or quota increases.

  3. In your support request, be sure to include:

    • The specific quota you want to increase (On-demand InvokeModel requests per minute)
    • The model ID (Anthropic Claude 3.5 Sonnet v2)
    • The AWS Region where you need the increase
    • A clear explanation of your use case, detailing why you need higher quotas for developing AI chat assistants
  4. Explain your current usage and the performance issues you're facing due to the current limits.

  5. Specify the desired quota increase you're requesting.

AWS will review your request carefully. Approval is not guaranteed and may take some time, as they need to ensure proper resource allocation. While waiting for a response, you might consider using a multi-account strategy as a temporary solution, since token limits are account-level.

For high-throughput requirements, you could also explore Provisioned Throughput options, though this comes with additional costs and may not be suitable for all use cases.

Remember, AWS typically looks for accounts to be utilizing a high percentage (often 80-90%) of their current quota before approving significant increases, so be prepared to justify your need for the increased capacity.
Sources
How to increase AWS Bedrock quota for the specific model? | AWS re:Post
Request to Increase Low Service Quotas for On-Demand InvokeModel Requests and Bedrock API on New Root Account | AWS re:Post

已回答 2 年前

專家

已審閱 2 年前

0

Hello.

Please contact AWS Support from the URL below.
https://support.console.aws.amazon.com/support/home#/

When making an inquiry, I think there will be no problem if you select the items below.
a

專家

已回答 2 年前

您尚未登入。 登入 去張貼答案。

一個好的回答可以清楚地回答問題並提供建設性的意見回饋,同時有助於提問者的專業成長。