Oriel — AI & technology worth noticing, every day.

Introducing Kimi K3.1 Pro on Amazon Bedrock

Web page · https://aws.amazon.com/blogs/machine-learning/introducing-kimi-k3-1-pro-on-amazon-bedrock

Kimi K3.1 Pro from Moonshot AI is now available on Amazon Bedrock. Learn how to get started through the OpenAI-compatible Chat Completions, Responses, and Converse APIs, optimize inference with explicit prompt caching, and use the model as a coding assistant in OpenCode.

First seen by Oriel on .

AI summary

Amazon Bedrock now offers Moonshot AI’s Kimi K3.1 Pro Highspeed, a faster post-trained model for long-context agentic, professional, and coding workloads.

  • Kimi K3.1 Pro Highspeed retains Kimi K3’s 3T-class open-weight architecture and 1-million-token context window, with additional post-training compute.
  • Moonshot AI reports two to three times the output speed of Kimi K3.1 Pro, targeting long-horizon agents, fewer factual errors, and specialized coding tasks.
  • The model supports tool calling, structured output, configurable reasoning, image input, streaming, and OpenAI-compatible Chat Completions and Responses APIs.
  • Flex serves requests at half the Standard price but may increase response times, making it suitable for evaluations, summarization, and background agent tasks.
  • Explicit prompt caching can reuse stable prefixes for at least 30 minutes, reducing latency and input cost, though cache writes cost more and require 256 tokens minimum.

#amazon bedrock #kimi k3.1 #llm agents #prompt caching

Generated by gpt-5.6-sol. Check the original for details.

Aliases

SourceExternal IDURL
AWS Machine Learning Bloga1657d26dd7d2a16f20836a0d0a5e765a3ee4064https://aws.amazon.com/blogs/machine-learning/introducing-kimi-k3-1-pro-on-amazon-bedrock/ Read discussion