Kimi K3.1 Pro Highspeed launches on Bedrock, CLI supports native integration
Understand this story
Moonshot AI's Kimi K3.1 Pro Highspeed is now available on Amazon Bedrock, retaining Kimi K3's 3T-class open-weight architecture and 1 million token context window, and is said to have optimized long-horizon agent tasks and factual accuracy through more post-training compute. On Bedrock, the model uses the same endpoints, APIs, and features as Kimi K3; the Flex tier offers the model at half the standard price, at the cost of potentially longer response times, on-demand quotas are shared across the Standard, Priority, and Flex tiers, and cache writes are billed higher than standard input. The subsequently released Kimi Code CLI v2.7.0 adds a native bedrock provider, allowing users to connect to models on Amazon Bedrock using the standard AWS credential chain (including named profiles and SSO), without needing to separately apply for and manage a Bedrock API key. The temporary API key generated by this provider is valid for up to 12 hours or until the AWS session ends, whichever is shorter; configuration requires explicitly specifying AWS_REGION or AWS_DEFAULT_REGION in config.toml or the shell environment. AWS says that the provider creation interfaces on Kimi Code's desktop and web versions do not yet expose all the environment fields required for this credential chain configuration.
AI overview based on source reports · Updated 10 hr ago
Developments
2 developments
- Nov 20 08:33 · 1 reportsIntroducing Kimi Code CLI native Bedrock provider usageAWS Machine Learning Blog:Use Kimi Code CLI with models on Amazon Bedrock
- Nov 11 09:07 · 1 reportsKimi K3.1 Pro Highspeed launches on Amazon BedrockAWS Machine Learning Blog:Introducing Kimi K3.1 Pro on Amazon Bedrock
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogUse Kimi Code CLI with models on Amazon Bedrock
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.
- AWS Machine Learning BlogIntroducing Kimi K3.1 Pro on Amazon Bedrock
Moonshot AI's Kimi K3.1 Pro Highspeed is now available on Amazon Bedrock, described as a post-trained version of Kimi K3 with the same 3T-class open-weight architecture and 1-million-token context window, trained with more post-training compute for long-horizon agentic work and fewer factual errors. It generates output tokens at a higher rate, with Moonshot AI reporting 2–3 times the speed of Kimi K3.1 Pro, and uses the same endpoint, APIs, and features as Kimi K3, so existing code can switch by changing the model ID. The post covers getting started via the Chat Completions, Responses, and Converse APIs, lowering costs with the Flex tier, explicit prompt caching, and using the model in OpenCode.
Activity for this story
- Current comparable activity
- 7
- Peak comparable activity
- 10Nov 20 10:00
- Change in the past 24 hours
- –
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.