GovCloud changelog

Claude Opus 5.5, Anthropic's most capable Opus model yet, is now available in the Kiro IDE and CLI across AWS GovCloud (US-East) and AWS GovCloud (US-West). It improves on Opus 5 for long-running agentic coding work and thinks adaptively on every request, deciding how much effort each task needs. It includes a 1M-token context window with a 2.0x credit multiplier, down from Opus 5's 2.2x. Update to the latest IDE or CLI version, then restart it to access the model from the model selector. Learn more ->

Claude Sonnet 5.5 is now available in the Kiro IDE and CLI across AWS GovCloud (US-East) and AWS GovCloud (US-West). It is Anthropic's fastest Sonnet model to date and a natural upgrade for teams already using Sonnet 5: output is more than 30% faster, real-world coding and knowledge work approaches Opus 5.5 performance, and writing is clearer. It is available with a 1M-token context window and a 1.3x credit multiplier. Update to the latest IDE or CLI version, then restart it to access the model from the model selector. Learn more ->

Claude Opus 4.8 and Claude Sonnet 5 are now available in the Kiro IDE and CLI across AWS GovCloud (US-East) and AWS GovCloud (US-West). Opus 4.8 brings stronger self-verification, efficient tool calling, and better follow-through on complex multi-step tasks, with a 1M context window and 2.2x credit multiplier. Sonnet 5 approaches Opus 4.8 on reasoning and agentic coding at lower cost, with a 1M context window, 1.3x credit multiplier, and experimental support. Update to the latest IDE or CLI version, then restart it to access the models from the model selector. Learn more ->

Kiro Enterprise administrators in AWS GovCloud (US) can now monitor organizational usage through the Kiro console. The usage dashboard provides aggregate metrics; daily per-user activity reports deliver credits, model usage, and other telemetry as CSV files to an Amazon S3 bucket in your account. Administrators can also enable prompt logging to capture user prompts and Kiro responses for compliance and debugging. Kiro does not charge for these monitoring features beyond the associated Amazon S3 storage costs. Learn more ->

OpenAI GPT-5.4 and NVIDIA Nemotron 3 Super 120B are now available in the Kiro IDE and CLI for AWS GovCloud (US-West). GPT-5.4 supports complex reasoning, coding, document analysis, and multi-step agentic workflows with a 272K context window and 1.2x credit multiplier. Nemotron 3 Super 120B is an open weight option with a 256K context window, 32K maximum output, and 0.25x credit multiplier. Update to the latest IDE or CLI version, then restart it to access the models from the model selector. Learn more ->

Kiro is now authorized for FedRAMP High and Department of Defense Cloud Computing Security Requirements Guide Impact Levels 4 and 5 in AWS GovCloud (US). Federal agencies, public sector organizations, and enterprises with these compliance requirements can use the Kiro IDE and CLI for sensitive development workloads within AWS GovCloud (US).

Model availability in Kiro does not by itself indicate that a specific model carries FedRAMP High or DoD IL-4/5 authorization. Only models explicitly listed within the Amazon Bedrock service scope carry those authorizations. Learn more ->

Kiro is now available in AWS GovCloud (US-East) and AWS GovCloud (US-West) regions, enabling government agencies and contractors to use Kiro within their compliance boundaries.

Authenticate using AWS IAM Identity Center with a GovCloud Start URL (containing us-gov-home). Kiro uses the same installer for both commercial and GovCloud regions—IAM Identity Center authentication automatically routes traffic to the appropriate region. Individual login methods like GitHub, Google, and AWS Builder ID are not available in GovCloud regions. Learn more ->

For GovCloud customers, inference requests are processed using Amazon Bedrock in AWS GovCloud (US-West). Your content remains stored in the region where your Kiro profile was created, with all cross- region communication encrypted via TLS 1.2+. Learn more ->