Introducing Kimi K3.1 Pro on Amazon Bedrock
Kimi K3.1 Pro from Moonshot AI is now available on Amazon Bedrock. Learn how to get started through the OpenAI-compatible Chat Completions, Responses, and Converse APIs, optimize inference with explicit prompt caching, and use the model as a coding assistant in OpenCode.
Kimi K3.1 Pro Highspeed, a high-performance model from Moonshot AI, has been launched on Amazon Bedrock. This variant of the K3.1 series is a post-trained version of Kimi K3, boasting a larger context window and enhanced capabilities for long-horizon agentic tasks, reduced factual errors, and improved performance in professional applications such as financial modeling, office documents, gaming engine coding, 3D scene creation, and CAD scripts.
The model operates at a faster rate, delivering 2-3 times the speed of its predecessor, Kimi K3.1 Pro. Kimi K3.1 Pro Highspeed operates using the same endpoint, APIs, and features as Kimi K3 on Amazon Bedrock. Users can easily adopt the new model by simply changing the model ID in their existing code. The model supports essential features including tool calling, structured output, configurable reasoning, image input, and streaming, and can be used without altering the existing security posture.
Moonshot AI emphasizes that user data remains within the AWS data boundary, is not shared with Moonshot AI, and is not used for model training. The model comes with zero data retention by default and ensures operator access is restricted, preventing AWS operators from viewing prompts and completions during inference. This guide explains how to get started with Kimi K3.1 Pro Highspeed on Amazon Bedrock, covers cost-saving strategies using the Flex tier, and demonstrates the model's utility as a coding assistant in OpenCode.
Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.