InvokeModel quota is 0

Hello.

Since you've already contacted AWS support, I think all you can do is wait for their response.
Also, please note that Bedrock quota requests may be rejected depending on the use case and usage, as described in the following documentation. https://docs.aws.amazon.com/bedrock/latest/userguide/quotas-increase.html

Due to overwhelming demand, priority will be given to customers who generate traffic that consumes their existing quota allocation. Your request might be denied if you don't meet this condition.

I understand your frustration with the InvokeModel quota showing as 0 and experiencing throttling errors. This situation typically occurs when model access hasn't been fully provisioned in your account, even though you can see the model catalog and Playground.

Here are some additional steps you can take while waiting for your support cases to be resolved:

Verify Model Access: First, double-check that you've properly requested and received access to the specific Anthropic Claude models you want to use. In the Amazon Bedrock console, go to "Model access" in the left navigation pane and ensure the Claude models show as "Access granted" (not just "Available to request"). Sometimes there's a delay between requesting access and it being fully activated.

Check the Correct Region: Ensure you're operating in an AWS region where Amazon Bedrock and your desired Claude models are available. Model availability and quotas are region-specific, so verify you're checking Service Quotas in the same region where you're trying to invoke the models.

Request Quota Increases: Even though your quotas show as 0, try submitting a quota increase request through the Service Quotas console for the specific runtime quotas (TPM and RPM) you need. This creates an additional ticket that may help expedite the resolution.

Escalate Your Support Cases: Since your support cases from April 19 and 21 are still unassigned, consider updating them with additional details about the urgency of your situation. If you have a Business or Enterprise support plan, you can also try reaching out through your Technical Account Manager (TAM) if available.

The fact that your runtime quotas are showing as 0 does suggest a provisioning issue that AWS Support will need to resolve, so continuing to follow up on your existing cases is important.

Hi,

I would like to clarify that this does not appear to be a model access issue.

Model access has already been granted I am able to list models and inference profiles successfully via CLI I am using the correct region (ap-southeast-1) However, all invocations return: "ThrottlingException: Too many tokens per day"

In Service Quotas, the applied account-level quota value is 0. This indicates that Bedrock inference quota has not been initialized for this account, rather than a model access delay.

Additionally:

The quotas are marked as "Not adjustable" Therefore, I am unable to request an increase via Service Quotas console Given this, it seems this requires backend provisioning by your team.

We are currently on AWS Business Support, and this issue is blocking all development as Bedrock inference cannot be used at all.

Could you please help:

Escalate this to the Bedrock service team Initialize baseline inference quota for this account Thank you.