# AWS tests show how reasoning effort and service tiers change Bedrock costs

_Published Thursday, November 12, 2026 at 4:09 PM EST · AI · Latest · Tier 2 — Notable_

![AWS tests show how reasoning effort and service tiers change Bedrock costs — Primary](https://d2908q01vomqb2.cloudfront.net/f1f836cb4ea6efb2a0b1b99f41ad8b103eff4b59/2026/11/10/ML-21479-featured-image-1.png)

AWS reported that Claude Opus 5 used 169% more median output tokens at high reasoning effort than at low effort in a Bedrock agent test, with all 24 runs correct at each level. Reasoning tokens are billed as output tokens, making the setting a direct cost variable.

In a separate Nova 2 Lite test, AWS said Flex requests cost half the Standard rate, with equal token counts. The findings depend on workload and model support: the code-generation test showed no reliable token difference between low and high effort, and unsupported Flex requests fail rather than fall back automatically.

## Sources

- [AWS Machine Learning Blog](https://aws.amazon.com/blogs/machine-learning/four-amazon-bedrock-inference-choices-that-affect-cost/)

---
Canonical: https://techandbusiness.org/newswire/wB1PNIgiGRgE9KYZxRgBQP
Published: 2026-11-12T21:09:13.000Z
Story chronology: 2026-11-12T20:51:55.000Z
Retrieved: 2026-11-12T22:46:02.197Z
Publisher: Tech & Business (techandbusiness.org)