Models

Kiro gives you access to frontier and open weight AI models from OpenAI, Anthropic, and other providers. GPT-5.6 brings OpenAI models to Kiro for the first time, with three tiers that balance agentic performance and cost. Pick the right model for the job, or select Auto to let Kiro route each task to the optimal model automatically.

† Claude Fable 5.1 is rolling out in a limited Preview for Kiro Enterprise customers. Administrators enable access through model governance.

Claude Fable 5.1 is rolling out gradually to Kiro Enterprise organizations with model governance enabled. It has a 1M context window and a 6x credit multiplier. Inference runs only in US East (N. Virginia) (us-east-1). Organizations with access can add Fable 5.1 from Manage approved list and make it available to their users. See Claude Fable 5.1 for capabilities and data-handling details.

US and EU are commercial geographies, each spanning several AWS Regions rather than a single Region. For the Regions in each geography and the endpoint that serves your requests, see Inference endpoint regions.

Cost is relative to Auto (1.0x baseline). For example, a task that costs 10 credits on Auto would cost 20 credits on Opus 5.5, 22 credits on Opus 5, 4 credits on Haiku, or 0.5 credits on Qwen3 Coder Next.

* GPT-5.6 uses OpenAI and Amazon Bedrock's two-tier context pricing model: requests up to 272K tokens use the listed short context rate, and requests over 272K tokens are billed at double that rate (Sol 8.8x, Terra 4.4x, Luna 1.2x).

AWS GovCloud (US) has a separate model catalog and Region-specific availability. See AWS GovCloud (US) models for the current model list, East and West availability, access requirements, and model-authorization guidance.

The geography that serves requests from commercial profiles depends on both the model and the Kiro profile Region. GPT-5.6 models are served from the US regardless of profile Region, Claude Fable 5.1 is available only in US East (N. Virginia), and every other model is served from the geography that matches the profile.

Profile Region applies to enterprise users who sign in through IAM Identity Center or an external identity provider. Free Tier users and individual subscribers are always served from the commercial US geography.

Kiro is powered by Amazon Bedrock, which uses cross-region inference to distribute requests across the Regions within a geography. Your request can be processed in any Region listed for your geography.

Cross-region inference does not change where your data is stored. For commercial profiles, models marked experimental are an exception to the table above: they may be processed in commercial AWS Regions worldwide, including outside your profile's geography. This exception does not apply to AWS GovCloud (US). See data protection for the full reference, Kiro in AWS GovCloud (US) for GovCloud behavior, and Amazon Bedrock cross-Region inference for how inference profiles route requests.

Model availability can vary by country or region. Kiro's model offerings align with each provider's usage and geographic requirements. For more information, see supported countries and regions: OpenAI, Anthropic, MiniMax, Zhipu AI (GLM), DeepSeek, and Qwen.

For models that support configurable reasoning effort, you can control how much reasoning the model applies to your prompts. Lower effort levels produce faster, shorter responses and use fewer credits. Higher levels spend more tokens on deeper analysis, multi-step reasoning, and thorough code generation.

In the IDE, set the level with the Effort slider below the model list in the Model panel. In Kiro CLI, open /model and choose Effort, or use the --effort launch flag. In Kiro Web, use the reasoning effort selector. The IDE choice applies to subsequent messages in the conversation. In CLI, effort chosen through /model persists for that model. Direct /effort <level> changes only the current session unless you then run /effort set-current-as-default; in V3, --effort is also session-only. Web choices apply to the current session. Each picker shows only levels supported by your current model. See Reasoning effort for the full reference: per-surface mechanics, supported models, persistent per-model defaults, thinking behavior, and precedence.

• Start with Auto for most work. It optimizes both quality and cost automatically.
• Use GPT-5.6 Sol for the hardest multi-step work - long-horizon refactors and complex terminal tasks where you need state-of-the-art agentic performance.
• Use GPT-5.6 Terra or Luna when you want strong agentic capability with throughput or cost as the primary concern. Terra for balanced performance, Luna for maximum efficiency.
• Use Opus 5.5 when you hit a wall on a complex problem, need sustained multi-file work, or want stronger self-verification and clearer communication across a long task.
• Use Sonnet 5.5 for fast, scoped coding, bug fixes, review, agent and subagent work, or focused documentation, slides, and spreadsheets.
• Use Haiku for quick iterations, simple fixes, or when you want to conserve credits.
• Monitor your usage in your account settings to understand how model choice affects consumption.
• Factor model cost into your tier: If you primarily use Opus, consider Pro+, Pro Max, or Power for more credits. See plans and billing for details.

For detailed descriptions of each model's capabilities, strengths, and lifecycle status, see Available models.