Kimi K3.1 Pro (Highspeed) now available on Amazon Bedrock
Moonshot AI’s Kimi K3.1 Pro (Highspeed) is now accessible on Amazon Bedrock, enabling faster agentic workflows with high output token rates and a one-million-token context window.
Amazon Bedrock now hosts Kimi K3.1 Pro from Moonshot AI, adding an open-weight model to its portfolio while maintaining the security and governance features customers expect. The model supports agentic tasks such as coding and document processing, delivering high output tokens per second for quicker responses. It operates within the same security framework as proprietary models on Amazon Bedrock, ensuring consistent compliance standards. Users can access the model through the Amazon Bedrock console across all supported AWS Regions.
Kimi K3.1 Pro is described by Moonshot AI as an open-weight, natively multimodal agentic model with a one-million-token context window, representing its most capable 3-trillion-parameter-class model to date. The company highlights improvements in coding, 3D creation, and financial research workflows. On Amazon Bedrock, the model benefits from explicit prompt caching to reduce latency and lower input costs. Cross-Region inference allows users to run the model in any AWS Region where Amazon Bedrock is available.
Moonshot AI reports that Kimi K3.1 Pro delivers high output tokens per second, enabling faster and more responsive agentic use cases on Amazon Bedrock. The model’s one-million-token context window supports extended document processing and complex coding tasks. Security and governance controls remain consistent with those applied to proprietary models within Amazon Bedrock. Explicit prompt caching further enhances performance by reducing latency and input expenses.
To begin using Kimi K3.1 Pro on Amazon Bedrock, customers can visit the Amazon Bedrock console or consult the Amazon Bedrock documentation for detailed guidance. The model is accessible in all AWS Regions where Amazon Bedrock operates, including cross-Region inference capabilities. Moonshot AI emphasizes the model’s agentic strengths in coding, 3D creation, and financial research. Security and governance features align with those of proprietary models on the platform.