AWS brings GLM 5.3 to Amazon Bedrock with managed APIs, cross-Region inference and prompt caching

What changed

AWS announced on October 5 that Z.ai's GLM 5.3 is now available on Amazon Bedrock. AWS describes it as a 753B-parameter mixture-of-experts model optimized for coding and long-horizon agentic workloads. Bedrock provides fully managed APIs, cross-Region inference, prompt caching and service tiers, with access through OpenAI-compatible Responses/Chat Completions as well as Bedrock Invoke/Converse interfaces. This entry records GLM 5.3's managed availability on Bedrock, not a claim that the model itself first launched on October 5.