- Newest
- Most votes
- Most comments
To address your issue with the low service limit for Cross-region model inference requests per minute for Anthropic Claude 3.7 Sonnet V1, you're correct that this quota is not directly adjustable through the standard Service Quotas process. However, there are steps you can take to potentially increase this limit:
-
Contact AWS Support: Even though the quota is marked as not adjustable, AWS Support may be able to assist you. You should open a case with AWS Support under the "Account and billing" category. This can typically be done free of charge.
-
Provide detailed information: When contacting support, be prepared to explain your use case, why the current limit is insufficient, and how you plan to use the increased capacity. This information helps AWS understand your needs better.
-
Engage your AWS account team: If you have an AWS account manager, Technical Account Manager (TAM), or Solutions Architect (SA), reach out to them directly. They can often advocate on your behalf and initiate an internal quota increase request process.
-
Be patient: Quota increase requests, especially for newer or high-demand services like Claude 3.7 Sonnet V1, may take some time to process. AWS needs to balance resource allocation across all customers.
-
Consider alternatives: While waiting for a potential increase, you might want to explore using other models available in Amazon Bedrock that have higher quotas or are more easily adjustable.
Regarding accessing the model through Anthropic directly instead of Bedrock, this wouldn't necessarily guarantee higher limits. Each platform has its own quota system, and Anthropic also implements rate limits for their API.
Remember that quota increases are not guaranteed and depend on various factors, including overall service capacity and demand. If your business case is critical, make sure to emphasize this when communicating with AWS Support or your account team.
Sources
Amazon Bedrock endpoints and quotas - AWS General Reference
Request to Increase Low Service Quotas for On-Demand InvokeModel Requests and Bedrock API on New Root Account | AWS re:Post
How do I restore Amazon Bedrock service quotas to their default levels? | AWS re:Post
Seeking Escalation Advice: Claude Opus Quota Limits Unexpectedly Set to Zero | AWS re:Post
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.
Relevant content
- asked 7 months ago
- AWS OFFICIALUpdated 6 months ago
- AWS OFFICIALUpdated 7 months ago
