Moonshot AI has released Kimi K3.1 Pro Highspeed on Amazon Bedrock. This model is a post-trained iteration of Kimi K3, maintaining the same 3T-class open-weight architecture and a 1-million-token context window. It incorporates substantially more post-training compute to enhance its capabilities.
The additional training for Kimi K3.1 Pro Highspeed focuses on improving long-horizon agentic work and reducing factual errors. It also shows better performance in professional tasks such as financial modeling and office document processing, as well as coding for game engines, 3D scenes, and computer-aided design (CAD) scripts. Moonshot AI reports that Kimi K3.1 Pro Highspeed generates output tokens 2-3 times faster than Kimi K3.1 Pro.
Kimi K3.1 Pro Highspeed uses the same endpoint, APIs, and features as Kimi K3 on Amazon Bedrock, allowing existing users to switch by changing the model ID. The model supports tool calling, structured output, configurable reasoning, image input, and streaming. Data processing occurs within the AWS data boundary, is not shared with Moonshot AI, and is not used for model training. Zero data retention and zero operator access are enabled for inference requests.
Users can access Kimi K3.1 Pro Highspeed via the Amazon Bedrock console playground or programmatically through the bedrock-runtime endpoint. It is available via OpenAI-compatible Chat Completions and Responses APIs, and Amazon Bedrock Converse and Invoke APIs. Cross-Region inference profiles include 'global.moonshotai.kimi-k3.1' for general workloads, and 'us.moonshotai.kimi-k3.1' and 'in.moonshotai.kimi-k3.1' for data residency requirements in the US and India, respectively.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's briefNew every morning, and the back catalogue is archived by date.
Moonshot AI's Kimi Code CLI version 2.7.0 now includes a native Amazon Bedrock provider, allowing users to connect to Bedrock models using existing AWS credential chains. This update removes the need for a separate Amazon Bedrock API key, simplifying authentication and credential management for AWS customers. The change improves security by reducing reliance on manually managed API keys and aligning with AWS's recommendation for short-term credentials.
Moonshot AI has made its Kimi K3.1 Pro Highspeed large language model available on Amazon Bedrock. This new model, part of the K3.1 series, offers improved performance for long-horizon agentic work, professional tasks, and coding, along with 2-3 times faster output generation compared to Kimi K3.1 Pro.