---
type: "raw_signal"
id: "introducing-glm-5-3-on-amazon-bedrock-9b0d2e"
slug: "introducing-glm-5-3-on-amazon-bedrock-9b0d2e"
title: "Introducing GLM 5.3 on Amazon Bedrock"
description: "AWS says GLM 5.3 from Z.ai is now available on Amazon Bedrock."
retrieval_nugget: "AWS says GLM 5.3 from Z.ai is now available on Amazon Bedrock."
observed_at: "2026-10-06"
record_date: "2026-10-06"
date_kind: "observed_at"
why_it_matters: "AWS says GLM 5.3 from Z.ai is now available on Amazon Bedrock. The company describes it as a 753-billion-parameter mixture-of-experts model for coding and long-horizon agentic tasks. The announcement points to invocation through OpenAI-compatible APIs and mentions prompt caching as a way to reduce cost and latency. It also describes an authorized security test using the open-source Strix agent. Th"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "aws.amazon.com"
topics: []
entities: []
related_patterns: []
source_url: "https://aws.amazon.com/blogs/machine-learning/introducing-glm-5-3-on-amazon-bedrock"
source_urls: ["https://aws.amazon.com/blogs/machine-learning/introducing-glm-5-3-on-amazon-bedrock"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:introducing-glm-5-3-on-amazon-bedrock-9b0d2e"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/introducing-glm-5-3-on-amazon-bedrock-9b0d2e/","markdown":"https://newruntime.com/signals/introducing-glm-5-3-on-amazon-bedrock-9b0d2e.md","json":"https://newruntime.com/signals/introducing-glm-5-3-on-amazon-bedrock-9b0d2e.json"}
---

# Introducing GLM 5.3 on Amazon Bedrock

## Retrieval answer

AWS says GLM 5.3 from Z.ai is now available on Amazon Bedrock.

AWS says GLM 5.3 from Z.ai is now available on Amazon Bedrock. The company describes it as a 753-billion-parameter mixture-of-experts model for coding and long-horizon agentic tasks. The announcement points to invocation through OpenAI-compatible APIs and mentions prompt caching as a way to reduce cost and latency. It also describes an authorized security test using the open-source Strix agent. The supplied source excerpt establishes the availability announcement and the features AWS highlights; it does not provide benchmark results, measured savings, or independent validation of model performance.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)