Verified, then logged.
Sun 22 Nov 2026 · 00:21 KST / 15:21 UTC한국어 | ENSearch /

Breaking02 / IT

AWS adds Kimi K3.1 Pro Highspeed to Amazon Bedrock

Existing API calls remain compatible, while Flex pricing cuts costs in exchange for potentially longer response times.

A tax specialist, seen from behind in an office, faces a monitor showing a blurred transaction dashboard and chat assistant panel, with a blank ID badge beside the keyboard. AI-generated image

AWS announced on 11 Nov that it had expanded the Kimi model range on Amazon Bedrock. Existing users can now select Kimi K3.1 Pro Highspeed, according to the announcement.

Compatibility. AWS documentation says the model uses the same endpoint and APIs as Kimi K3. Existing code needs only a change to the model ID.

AWS says its Flex tier costs half the Standard price. Response times may be longer. Applications can select a tier for each request.

AWS says input data stays within its data boundary. It is not shared with Moonshot AI or used to train the model.

AWS describes the new model as a version of Kimi K3 with further training. It retains the same open-weight architecture, meaning the model's trained parameters are publicly available.

Execution environment. According to AWS documentation, the OpenCode coding agent runs in a local terminal. It calls the model through the Bedrock API.

AWS's post does not disclose deployment procedures for local inference or the licence terms governing use of the weights.