Models changelog

Added support for GLM-5, a sparse mixture-of-experts model with a 200K context window designed for complex systems engineering and long-horizon agentic tasks. GLM-5 excels at processing repository-scale context and maintaining coherence during multi-step tool use across large codebases, making it a strong choice for cross-file migrations, full-stack feature development, and legacy refactoring where the model needs to hold the full picture. Available with experimental support in both the Kiro IDE and Kiro CLI. Inference runs in us-east-1 (N. Virginia) with a 0.5x credit multiplier. Restart your IDE or CLI to access it from the model selector. Learn more ->

Claude Opus 4.6 and Claude Sonnet 4.6 now support a 1M context window, up from 200K, and are no longer marked as experimental. Both models are now generally available in the Kiro IDE and Kiro CLI for Pro, Pro+, and Power tier subscribers.

Restart your IDE or CLI to see the updated models. Learn more ->

MiniMax M2.5 is now available in eu-central-1 (Frankfurt) for users authenticating with AWS IAM Identity Center, extending support beyond us-east-1 (N. Virginia).

Available on all subscription tiers with a 0.25x credit multiplier and 200K context window. Restart your IDE or CLI to access it from the model selector. Learn more ->

A new open weight model is now available with experimental support in the Kiro IDE and CLI. Available on Free, Pro, Pro+, and Power tiers with all authentication methods. Supported in us-east-1 (N. Virginia). Restart your IDE or CLI to access it from the model selector.

MiniMax M2.5 matches frontier-class coding performance at a fraction of the cost. Trained with reinforcement learning across hundreds of thousands of real-world environments, it delivers strong results across the full development lifecycle from system design to code review and completes complex agentic tasks significantly faster than its predecessor. 200K context window with a 0.25x credit multiplier.

MiniMax 2.1, DeepSeek 3.2, and Qwen3 Coder Next are now available for AWS IAM Identity Center users. All three open weight models are available on all plans in both the Kiro IDE and CLI. MiniMax 2.1 and Qwen3 Coder Next are available in both us-east-1 (N. Virginia) and eu-central-1 (Frankfurt). DeepSeek 3.2 is available in us-east-1 only. Credit multipliers are unchanged: DeepSeek 3.2 at 0.25x, MiniMax 2.1 at 0.15x, and Qwen3 Coder Next at 0.05x. Learn more ->

Added support for Claude Sonnet 4.6, a full upgrade from Sonnet 4.5 that approaches Opus 4.6 intelligence while being more token efficient. Sonnet 4.6 excels at iterative development workflows, maintains context across long sessions, and handles both lead agent and subagent roles in multi-model pipelines. Well-suited for teams using Kiro powers and custom subagents.

Available with experimental support in both the Kiro IDE and Kiro CLI for Pro, Pro+, and Power tier subscribers signing in with Google, GitHub, AWS Builder ID, AWS IAM Identity Center, or external IDP. Supported in us-east-1 (N. Virginia) and eu-central-1 (Frankfurt) with a 1.3x credit multiplier. Restart your IDE to access it from the model selector. Learn more ->

You can now choose from three open weight models in the Kiro IDE and Kiro CLI. Available with experimental support on all plans, with sign-in via Google, GitHub, or AWS BuilderID. Inference runs in US East (N. Virginia). Restart your IDE to access them from the model selector. Learn more ->

0.25x credit multiplier. Best suited for agentic workflows and code generation. Handles long tool-calling chains, stateful sessions, and multi-step reasoning well. Learn more ->

0.15x credit multiplier. Best suited for multilingual programming and UI generation. Delivers strong results across Rust, Go, C++, Kotlin, TypeScript, and others. Learn more ->

0.05x credit multiplier. Purpose-built for coding agents with 256K context and strong error recovery. Works especially well for long agentic coding sessions in the CLI. Learn more ->

Added support for Claude Opus 4.6 in eu-central-1 for users authenticating with IAM Identity Center_** **_— Anthropic's smartest model with state-of-the-art coding and agentic capabilities. Opus 4.6 plans more carefully, sustains tasks for longer, operates reliably in larger codebases, and catches its own mistakes through better debugging. Available with experimental support in both the Kiro IDE and Kiro CLI for Pro, Pro+, and Power tier subscribers with a 2.2x credit multiplier. Restart your IDE to access it from the model selector.

Added support for Claude Opus 4.6 — Anthropic's most powerful model and the world's best for coding. Opus 4.6 excels on large-scale codebases and long-horizon projects, making it ideal for spec-driven development and sophisticated agents. Available with experimental support in both the Kiro IDE and Kiro CLI for Pro, Pro+, and Power tier subscribers with a 2.2x credit multiplier. Supported in us-east-1 for users authenticating with IAM Identity Center. Restart your IDE to access it from the model selector.

We've added support for Claude Opus 4.5 to AWS IAM Identity Center users in both us-east-1 and eu-central-1 regions. Claude Opus 4.5 is available in both the Kiro IDE and Kiro CLI for Pro, Pro+, and Power tier subscribers.