Kimi K3.1 Pro Highspeed becomes available on Amazon Bedrock
AWS has made Moonshot AI’s Kimi K3.1 Pro Highspeed available through Amazon Bedrock, with image input and a 1-million-token context window.
AT A GLANCE
Key points
- 1-million-token context with text and image input
- Configurable reasoning and prompt caching on Bedrock
- US, India, and Global cross-Region inference profiles
What is changing?
AWS made Moonshot AI’s Kimi K3.1 Pro Highspeed available on Amazon Bedrock on November 6. The official model card lists the model as active and confirms text and image input, a 1-million-token context window, and support for the Responses, Chat Completions, Converse, and Invoke APIs.
Moonshot AI describes K3.1 Pro as a version of Kimi K3 developed with substantially more post-training compute and as its most capable 3-trillion-parameter-class open-weight model to date. The company says the Highspeed variant produces output two to three times faster than standard K3.1 Pro; this is a provider-reported performance claim.
On Bedrock, reasoning can be disabled or configured across six effort levels. The model supports implicit and explicit prompt caching, structured outputs, tool calling, Guardrails, and Standard, Priority, and Flex service tiers. Access is provided through US, India, and Global cross-Region inference profiles.
Explore the original sources
Source date: 6 November 2026.
Published by AI Radar: 11 Nov 2026, 05:10 (Istanbul, UTC+3).
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…