153. LLM Inference with Bedrock

If you’re curious about building with LLMs, but you want to skip the hype and learn what it takes to ship something reliable in production, this episode is for you.We share our real-world experience building AI-powered apps and the gotchas you hit after the demo: tokens and cost, quotas and throttling, IAM and access friction, marketplace subscriptions, and structured outputs that do not break your JSON parser.We focus on Amazon Bedrock as AWS’s managed inference layer: how to get started with the current access model, how to choose models, how pricing works, and what to watch for in production.We also go deep on structured outputs: constrained decoding, schema design that improves output quality, and how to avoid “grammar compilation timed out”. In this episode, we mentioned the following resources: fourTheorem: Bedrock structured outputs guide Amazon Bedrock Bedrock docs Bedrock pricing Structured outputs Cross-region inference Quotas Throttling help Prompt caching Troubleshooting error codes Do you have any AWS questions you would like us to address? Leave a comment here or connect with us on X/Twitter, BlueSky or LinkedIn: - ⁠ | ⁠ | ⁠ - ⁠ | ⁠ | ⁠

You can listen to 153. LLM Inference with Bedrock online on Radio and Podcast. Open the player on this page to stream the available audio.

153. LLM Inference with Bedrock is an episode from AWS Bites by AWS Bites.

This episode is 00:43:25 long.

This episode was published on Mar 6, 2026.

Yes. Use the heart button on the episode page to add it to your favorite episodes list.

Yes. This page shows related episodes from AWS Bites when more episodes are available from the podcast feed.