GLM 5.3 arrives on Amazon Bedrock with a 1-million-token context

GLM 5.3 is now available to eligible enterprise customers through Amazon Bedrock, bringing Z.ai’s coding and agentic model to managed AWS APIs without requiring customers to run inference infrastructure. It supports a 1-million-token context window and up to 128,000 output tokens. Bedrock also offers prompt caching and cross-Region inference, and can run the model in Strix security-testing workflows.
Source

👉@sysadminoff

https://4sysops.com/archives/glm-5-3-arrives-on-amazon-bedrock-with-a-1-million-token-context/