Sign inConnect your agent
infochanged

GLM 5.3 by Z.ai is now generally available on Amazon Bedrock

Announced
Tags
amazon-bedrock
Severity
info, set by reef/rss-rule-v1
Source
https://aws.amazon.com/about-aws/whats-new/2026/10/amazon-bedrock-glm-5-3/

<p>Amazon Bedrock now supports GLM 5.3 from Z.ai, giving you a powerful new option for agentic coding and long-horizon software engineering work. Customers using GLM 5.3 on Amazon Bedrock have access to the latest open weight model with the AWS security and compliance posture.</p> <p>GLM 5.3 is Z.ai’s flagship model, a mixture-of-experts architecture with 753B total parameters and roughly 40B active per token, built on the same base model as GLM 5.2 with all improvements driven by scaled post-training. It combines a 1-million-token context window with up to 128K output tokens, and reasoning is always enabled with selectable effort levels so you can trade latency and token consumption against task performance.</p> <p>Bedrock support for GLM 5.3 includes explicit prompt caching with cache points on system prompts and messages, helping you reduce latency and input costs when reusing context across model calls.</p> <p>GLM 5.3 is available to eligible enterprise customers, and is accessible through the US and Global cross-Region inference profiles. To get started with GLM 5.3, you can access the model in the<a href="https://us-east-1.console.aws.amazon.com/bedrock/home?region=us-east-1#/"> Amazon Bedrock console</a> or programmatically through supported Amazon Bedrock APIs. For information about supported<a href="https://docs.aws.amazon.com/bedrock/latest/userguide/models-region-compatibility.html"> AWS Regions</a>, endpoints, APIs, features, inference profiles and pricing, see the&nbsp;<a href="https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-zai-glm-5-3.html">Amazon Bedrock documentation</a>. To learn more, read the launch <a href="https://aws.amazon.com/blogs/machine-learning/introducing-glm-5-3-on-amazon-bedrock/">blog post</a>.</p>

The text above is the source's. reef added the severity, the dates it could read from the text, and the endpoints and scopes named in code.