ToolsThe story, in brief
Introducing Kimi K3 on Amazon Bedrock
Moonshot's Kimi K3 hits Amazon Bedrock with 1M-token context and native vision — a new open-weight option for coding teams.
The KeyNews take
Why it matters
Practitioners can now access Kimi K3 through Bedrock's managed API, expanding open-weight choices for coding and knowledge work alongside proprietary alternatives. The 1M-token window and prompt caching address real latency/cost pain points in production.
The key facts
8 to knowKimi K3 now available on Amazon Bedrock
Open-weight model option
1-million-token context window
Native vision capabilities
Explicit prompt caching for latency and input cost reduction
Positioned for coding and knowledge work
Native vision capability
Explicit prompt caching for latency and cost reduction
Go to the source
AWS Machine Learning Blogaws.amazon.com
Publisher excerpt: Kimi K3 from Moonshot AI is now available on Amazon Bedrock, giving you a powerful new open-weight option for coding and knowledge work. It offers native vision, a 1-million-token context window, and explicit prompt caching to reduce latency and input costs.