What changed
Moonshot AI's Kimi K3.1 Pro Highspeed is now available on Amazon Bedrock. This model is part of the K3.1 series and is a post-trained version of Kimi K3, with the same 3T-class open-weight architecture and 1-million-token context window. It is trained with substantially more post-training compute, which targets long-horizon agentic work and reduces factual errors. It also improves professional tasks such as financial modeling, office documents, and coding for game engines, 3D scenes, and computer-aided design (CAD) scripts. Kimi K3.1 Pro Highspeed generates output tokens at a higher rate and Moonshot AI reports 2–3 times the speed of Kimi K3.1 Pro.
What this means in practice
Kimi K3.1 Pro Highspeed uses the same endpoint, APIs, and features as Kimi K3 on Amazon Bedrock. Developers who already use Kimi K3 can try the new model by changing the model ID in their existing code. The model supports tool calling, structured output, configurable reasoning, image input, and streaming. Data is processed within the AWS data boundary and is not shared with Moonshot AI or used to train the model. Zero data retention is always enabled for inference requests, and AWS operators cannot view prompts and completions during inference.
Limitations and availability
Kimi K3.1 Pro Highspeed is available through cross-Region inference profiles: global.moonshotai.kimi-k3.1 routes requests to any supported commercial AWS Region and costs less per token than geographic profiles. It is recommended for most workloads. us.moonshotai.kimi-k3.1 keeps processing within US Regions, and in.moonshotai.kimi-k3.1 keeps it within India Regions for data residency requirements. The model can be accessed via the bedrock-runtime endpoint through the OpenAI-compatible Chat Completions and Responses APIs, and through the Amazon Bedrock Converse and Invoke APIs. The Flex tier offers half the Standard price for Kimi K3.1 Pro Highspeed, suitable for cost-sensitive workloads.
