Introducing Kimi K3.1 Pro on Amazon Bedrock
Machine Learning Blog
This article announces the availability of Kimi K3.1 Pro Highspeed on Amazon Bedrock, a post-trained model with enhanced capabilities for agentic work and professional tasks.
- Kimi K3.1 Pro Highspeed generates output 2–3 times faster than Kimi K3.1 Pro with improved reasoning and fewer factual errors
- Supports tool calling, structured output, configurable reasoning, image input, and streaming with same APIs as Kimi K3
- Data processed within AWS boundary, not shared with Moonshot AI, with zero data retention and operator access
- Flex tier pricing offers 50% cost reduction for latency-tolerant workloads like evaluations and background tasks
- Explicit prompt caching optimizes repeated context by caching stable prefixes for lower latency and input costs
- Available through cross-Region inference profiles: global, US-only, and India-only for data residency requirements
- Integrates with OpenCode terminal coding agent for improved agentic coding workflows
Kimi K3.1 Pro Highspeed enables faster, more cost-efficient AI development on Amazon Bedrock with enhanced security and flexible deployment options.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.