Understand this story
On November 20, 2026, Moonshot AI added a native Bedrock provider to Kimi Code CLI v2.7.0. AWS Machine Learning explained that users can connect Kimi Code CLI to Amazon Bedrock models using their existing AWS credentials, without separately managing Bedrock API keys. The provider supports the default credential chain, named profiles, and SSO, and can generate temporary bearer tokens valid for up to 12 hours without exceeding the AWS session duration. There are currently no other evidenced developments.
AI-generated from public reports
Latest development · Report
How to Use Kimi Code CLI to Access Models on Amazon BedrockDevelopments
1 confirmed developments
- Source:AWS Machine Learning
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 20
AWS Machine LearningFirst-party
How to Use Kimi Code CLI to Access Models on Amazon Bedrock
AWS explains how to connect Kimi Code CLI v2.7.0 to models on Amazon Bedrock using existing AWS credentials, eliminating the need to manage a separate Amazon Bedrock API key. The native Bedrock provider supports the default credential chain, named profiles, and SSO, and generates a temporary bearer token valid for up to 12 hours or no longer than the AWS session duration. Using Kimi K3.1 Pro Highspeed as an example, the article provides the IAM permissions, config.toml configuration, and connectivity testing workflow.
AI Trends