What was announced
Moonshot AI's Kimi K3.1 Pro Highspeed is now available on Amazon Bedrock. The model is part of the company's new K3.1 series and is a post-trained version of Kimi K3.
What changed
According to Moonshot AI, the model keeps the same 3T-class open-weight architecture and 1-million-token context window as Kimi K3, but was trained with substantially more post-training compute. That extra training targets long-horizon agentic work and fewer factual errors. The company also reports improvements in professional tasks such as financial modeling and office documents, plus coding for game engines, 3D scenes and CAD scripts.
The "Highspeed" variant generates output tokens at a higher rate; Moonshot AI claims 2-3x the speed of the standard K3.1 Pro.
What it means for developers
The model uses the same endpoint, APIs and features as Kimi K3 on Bedrock, so existing applications only need a model ID change. It supports tool calling, structured output, configurable reasoning, image input and streaming.
Access runs through cross-Region inference profiles: global.moonshotai.kimi-k3.1 routes requests to any supported commercial AWS Region at a lower per-token cost, while US and India profiles keep processing within those regions.
Data and security
AWS says data is processed within the AWS data boundary, isn't shared with Moonshot AI and isn't used to train the model. Zero data retention is always enabled for inference requests, and with zero operator access AWS staff can't view prompts and completions during inference.
