AgentCore Gateway now supports Bedrock InvokeModel APIs and model fallback

Amazon Bedrock AgentCore Gateway Updates

Amazon Bedrock AgentCore Gateway now supports the Amazon Bedrock InvokeModel and InvokeModelWithResponseStream APIs on its inference endpoint, along with model fallback routing for inference traffic.

With InvokeModel support, you can integrate with any model provider through a single governed endpoint without rewriting client code for each provider. Model fallback automatically routes requests to an alternative model or provider when the primary destination is throttled, out of capacity, or unreachable, ensuring your agents remain available.

For fallback routing, you define an ordered chain of alternative destinations in a gateway rule, along with conditions that trigger a switch, such as throttling, server errors, or response timeouts. A built-in circuit breaker skips failing destinations, ensuring requests reach a healthy destination faster.

What to do

• Update your SDK integration to use the new InvokeModel and InvokeModelWithResponseStream APIs.
• Configure model fallback rules in your gateway to ensure high availability.

Source: AWS release notes

If you need further guidance on AWS, our experts are available at AWS@westloop.io. You may also reach us by submitting the Contact Us form.