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 available to Kiro Enterprise customers. Administrators enable access through model governance.

Claude Fable 5.1 is generally available 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, 0.6 credits at Haiku 5.5's 0.06x rate for a request up to 100K tokens, or 0.5 credits on Qwen3 Coder Next.

* Two-tier context pricing applies to GPT-5.6 and Claude Haiku 5.5. GPT-5.6 requests up to 272K tokens use the listed rate; requests over 272K tokens are billed at double that rate (Sol 8.8x, Terra 4.4x, Luna 1.2x). Haiku 5.5 requests up to 100K tokens use the listed 0.06x rate; requests over 100K tokens are billed at 0.3x.

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 table below is the source of truth for model routing. Inference scope shows whether requests stay within the listed endpoint location or may route globally. The profile columns show the endpoint used for each Kiro profile Region. Lifecycle status and inference routing are independent.

Profile Region applies to enterprise users who sign in through IAM Identity Center or an external identity provider. Free Tier users and individual subscribers use the US endpoint.

Inference scope shows where requests may be processed:

• Geography: Within the endpoint geography shown in the row.
• Global: Across supported commercial AWS Regions worldwide, including outside the endpoint geography.

The Regions below support inference within each geography. Individual models may use one or more listed Regions.

Cross-region inference, including global routing, does not change where Kiro stores your data. For the full Global scope disclosure, see Global cross-region inference. Global routing does not apply to AWS GovCloud (US). See Kiro in AWS GovCloud (US) for GovCloud behavior and Amazon Bedrock cross-Region inference for how inference profiles route requests.

In a local V3 session, Kiro can move a turn to another model when the current model declines the request or is unavailable. The transcript names the model that continued and says whether the change applies to one turn or the rest of the conversation.

In Kiro IDE, a fallback inside a sub-agent appears inside that sub-agent's activity. A retry that keeps the same model appears as a temporary retry notice. In Kiro CLI, the final notice also lists the models tried and the outcome. In Kiro CLI 2.33 or later, a retry on Auto names no model, because the service picks the model; before 2.33, the notice named a model. See Kiro CLI model fallback notices for terminal behavior.

In Kiro CLI 2.33 or later, a V3 session can also choose its fallback: open /model, select the current model, and set the Fallback row, or run /model fallback <model-id>. Kiro saves the choice through the agent when the agent supports it; the choice applies to the current session and persists for later sessions. Before 2.33, a V3 session could not configure a fallback. To confirm the saved choice, run /model and read the Fallback row. See /model for the full command reference, including V1 and V2.

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 5.5 for high-volume work requiring quick responses.
• 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.