# AWS Adds Moonshot AI's Kimi K3 Model to Amazon Bedrock

> Amazon Web Services announced that Kimi K3, the latest large language model from Moonshot AI, is now available on Amazon Bedrock. The AWS Machine Learning Blog states that Kimi K3 is the first open model to reach 2.8 trillion parameters and supports a 1-million-token context window. AWS says the model also introduces prompt caching to reduce costs and latency, and offers enhanced security with zero data retention for inference requests.

- **Topic**: Models
- **Published**: 2026-09-21T02:14:36.193Z
- **Read Time**: 1 min read
- **Canonical URL**: https://highsignal.sh/stories/aws-adds-moonshot-ai-s-kimi-k3-model-to-amazon-bedrock-ffca2f8a

## Why It Matters

Adding Moonshot AI's Kimi K3 to Amazon Bedrock offers organizations a high-capacity, open-weight language model directly on AWS infrastructure with improved performance and security features.

## Key Findings & Analysis

### Kimi K3 Model Features

Kimi K3 is described by Moonshot AI as its most capable model to date, and the first open model to reach 2.8 trillion parameters. It includes native vision capabilities, a 1-million-token context window, and claims a 2.5x efficiency improvement over Kimi K2.

### Deployment, Security, and Cost Controls

AWS highlights that Kimi K3 brings explicit prompt caching, which aims to lower latency and input costs when reusing context. The platform enforces zero data retention and zero operator access for greater data security. Organizations can adopt Kimi K3 without changing their security posture.

## Original Evidence & Verbatim Citations

> "Today, Kimi K3 from Moonshot AI is available on Amazon Bedrock, giving you a powerful new option for coding and knowledge work."

— *Grounded field: headline*

> "According to Moonshot AI, Kimi K3 is its most capable model and the first open model to reach 2.8 trillion parameters."

— *Grounded field: summary*

> "It combines native vision capabilities with a 1-million-token context window and delivers an approximate 2.5x improvement in scaling efficiency over Kimi K2."

— *Grounded field: summary*

> "Kimi K3 is the first open-weight model on Amazon Bedrock to support explicit prompt caching, helping you reduce latency and input costs when reusing context across model calls."

— *Grounded field: summary*

> "Zero data retention is always enabled for inference requests, while zero operator access prevents even AWS operators from accessing your prompts and completions during inference."

— *Grounded field: summary*

> "These advances make Kimi K3 well suited to long-running coding and knowledge workflows that require sustained context across large repositories, documents, and images."

— *Grounded field: whyItMatters*

> "As with all open-weight models on Amazon Bedrock, you can adopt Kimi K3 without changing your security posture."

— *Grounded field: whyItMatters*

> "According to Moonshot AI, Kimi K3 is its most capable model and the first open model to reach 2.8 trillion parameters."

— *Grounded field: section:0*

> "It combines native vision capabilities with a 1-million-token context window and delivers an approximate 2.5x improvement in scaling efficiency over Kimi K2."

— *Grounded field: section:0*

> "Kimi K3 is the first open-weight model on Amazon Bedrock to support explicit prompt caching, helping you reduce latency and input costs when reusing context across model calls."

— *Grounded field: section:1*

> "Zero data retention is always enabled for inference requests, while zero operator access prevents even AWS operators from accessing your prompts and completions during inference."

— *Grounded field: section:1*

> "As with all open-weight models on Amazon Bedrock, you can adopt Kimi K3 without changing your security posture."

— *Grounded field: section:1*

## Primary Sources & Citations

- [Introducing Kimi K3 on Amazon Bedrock](https://aws.amazon.com/blogs/machine-learning/introducing-kimi-k3-on-amazon-bedrock/) — *AWS Machine Learning Blog* (Primary source)

---

[← Back to front page](https://highsignal.sh/) | [Daily Brief](https://highsignal.sh/brief) | [All stories](https://highsignal.sh/latest)