iCreatAI News
Skip to content
AWS Machine Learning Blog· Alex Thewsey·· 11 hr agoAI score28

Use Kimi Code CLI with models on Amazon Bedrock

Use Kimi Code CLI with models on Amazon Bedrock

AI summary

Kimi Code CLI v2.7.0 from Moonshot AI adds a native bedrock provider that authenticates through the standard AWS credential chain, including named profiles and SSO, instead of requiring a separately managed Amazon Bedrock API key. The provider resolves AWS credentials, generates a short-lived bearer token via @aws/bedrock-token-generator, builds the regional bedrock-runtime endpoint, and calls the selected inference profile, as shown with Kimi K3.1 Pro Highspeed on the global.moonshotai.kimi-k3.1 profile. The post covers prerequisites, an example IAM policy, config.toml setup, testing, and configuration best practices.

Source: AWS Machine Learning Blog · aws.amazon.com