Reasoning effort - Models - Docs - Kiro Loading image... Product * About Kiro * IDE * CLI * Web * Mobile * Crew * Pricing * Downloads For * Enterprise * Startups * Students Community * Overview * Ambassadors * Discord * Events * Powers * Shop * Showcase Resources * Docs * Blog * Changelog * FAQs * Report a bug * Suggest an idea * Billing support Social * * * * * * * English Site Terms License Responsible AI Policy Legal Privacy Policy Cookie Preferences English Loading image... * Apps * CLI * Web * Enterprise * Pricing * Docs * Community * Resources SIGN IN DOWNLOADS Loading image... Get Started Installation Authentication Your first project Models Overview Available models Reasoning effort Features How Kiro works Specs Steering Hooks MCP Permissions Custom agents Agent Skills Powers Cloud sessions Compaction Kiroignore Checkpoints and rewind Built-in tools Configuration scopes IDE 1.x What's new in 1.0 Setup & First Run Editor Chat Experimental Troubleshooting 0.x reference CLI What's new in 3.0 Setup & First Run Terminal UI Chat Voice mode Headless mode ACP Auto complete Experimental 2.x reference Crew Quick start Installation Running 24/7 Chat Agent Capabilities Features Interfaces Apps System & storage Configuration Security Troubleshooting Web Setup & First Run Identity Center Connect your repositories Working with the agent Autonomous mode Automations Memory Configuration Sync Sandbox Mobile - Preview Overview Commands and Reference CLI commands Slash commands Built-in tools Exit codes Settings Billing Overview Managing your subscription Upgrading your plan Downgrading your plan Cancelling your plan Purchasing add-on credits Managing your payments Managing usage notifications Managing your taxes Contacting billing support Deleting your account Related questions Enterprise Concepts Onboarding quickstart Connecting your identity provider Deployment options Subscribe your team Manage subscriptions Governance Monitor and track Settings Managed updates Billing IAM Supported regions Privacy and Security Overview Data protection Code references Compliance validation Infrastructure security IAM permissions Firewalls, proxies, and data perimeters VPC endpoints (AWS PrivateLink) Guides Overview Language support Learn by playing Migration Migrating from Q Developer Migrating from VSCode Upgrading from Q CLI * Docs * * Models * * Reasoning effort Copy page View as Markdown Reasoning effort Copy page View as Markdown Reasoning effort controls how much thinking 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. Capability IDE CLI Web Mobile Reasoning effort selection ✓ ✓ — — Available levels: Level Behavior low Fast, concise responses. Good for simple questions and quick lookups. medium Balanced reasoning. Suitable for most development tasks. high Thorough analysis. Better for complex refactoring and architecture decisions. xhigh Extended reasoning. Useful for multi-file changes and nuanced problems. max Maximum depth. Best for difficult debugging, security analysis, and intricate logic. Not all models support every level. The picker only shows levels available for your current model - see supported models below. Setting effort level IDE CLI Click the model name in the chat input bar to open the model selector, then choose an effort level from the Effort panel on the right side. Your effort selection appears next to the model name (e.g., "Claude Opus 4.6 · max") and applies to all subsequent messages in the conversation. Supported models Each model defines the values it accepts for the reasoning-related fields in its configuration schema. The output_config.effort column lists the effort levels available for that model; thinking.type and thinking.display control reasoning behavior and visibility; max_tokens sets the output length limit. Claude models use output_config.effort with thinking.type and thinking.display controls: Model thinking.type thinking.display output_config.effort max_tokens Claude Opus 5 adaptive , disabled summarized , omitted low , medium , high , xhigh , max 1024–128000 Claude Opus 4.8 adaptive , disabled summarized , omitted low , medium , high , xhigh , max 1024–128000 Claude Opus 4.7 adaptive , disabled summarized , omitted low , medium , high , xhigh , max 1024–64000 Claude Opus 4.6 adaptive , disabled summarized , omitted low , medium , high , max 1024–64000 Claude Sonnet 5 adaptive , disabled summarized , omitted low , medium , high , xhigh , max 1024–128000 Claude Sonnet 4.6 adaptive , disabled summarized , omitted low , medium , high , max 1024–64000 GPT-5.6 models use reasoning.effort : Model reasoning.effort GPT-5.6 Terra none , low , medium , high , xhigh , max GPT-5.6 Sol none , low , medium , high , xhigh , max GPT-5.6 Luna none , low , medium , high , xhigh , max GPT-5.6 models default to effort: "high" . Persisting your effort level (CLI) Your effort choice persists automatically. Set a level with /effort or --effort and Kiro remembers it for future sessions - there's no extra step to make it the default. Preferences are stored in ~/.kiro/settings/cli.json . See In-session settings for more on how preferences persist. Persistent defaults (CLI) To set default model parameters per model - so you don't have to run /effort at the start of every session - add chat.modelDefaults to your settings file: Claude models (use output_config.effort ): json { "chat.modelDefaults" : { "claude-sonnet-4.6" : { "output_config" : { "effort" : "high" } } , "claude-opus-4.7" : { "output_config" : { "effort" : "max" } } } } GPT-5.6 models (use reasoning.effort ): json { "chat.modelDefaults" : { "gpt-5.6-sol" : { "reasoning" : { "effort" : "max" } } , "gpt-5.6-terra" : { "reasoning" : { "effort" : "low" } } } } Configuring thinking behavior Control whether the model uses extended thinking and how it displays reasoning: json { "chat.modelDefaults" : { "claude-opus-4.8" : { "thinking" : { "type" : "adaptive" , "display" : "summarized" } } , "claude-sonnet-4.6" : { "thinking" : { "type" : "disabled" } } } } * thinking.type - adaptive enables extended thinking when the model determines it's needed; disabled turns it off entirely. * thinking.display - summarized shows a condensed version of reasoning; omitted hides it from output. Only applies when type is adaptive . Configuring max output tokens Set the maximum number of tokens the model can generate per response: json { "chat.modelDefaults" : { "claude-opus-4.8" : { "max_tokens" : 128000 } , "claude-sonnet-4.6" : { "max_tokens" : 32000 } } } max_tokens limits per model: Model Minimum Maximum Claude Opus 4.8 1024 128000 Claude Opus 4.7 1024 64000 Claude Opus 4.6 1024 64000 Claude Sonnet 5 1024 128000 Claude Sonnet 4.6 1024 64000 GPT-5.6 Terra 1024 128000 GPT-5.6 Sol 1024 128000 GPT-5.6 Luna 1024 128000 Combining all options You can combine output_config , thinking , and max_tokens in a single model entry: Claude example: json { "chat.modelDefaults" : { "claude-opus-4.8" : { "output_config" : { "effort" : "max" } , "thinking" : { "type" : "adaptive" , "display" : "summarized" } , "max_tokens" : 128000 } } } GPT-5.6 example: json { "chat.modelDefaults" : { "gpt-5.6-sol" : { "reasoning" : { "effort" : "max" } , "max_tokens" : 128000 } } } To open your settings file in your editor: bash kiro-cli settings open Or place a .kiro/settings/cli.json in your project root to set workspace-level defaults that apply to everyone working in that repository. Precedence When determining the effort level for a session, Kiro applies this priority order: * Session override - value set via the effort picker, /effort , or --effort during the current session * Workspace defaults - chat.modelDefaults in .kiro/settings/cli.json * User defaults - chat.modelDefaults in ~/.kiro/settings/cli.json * Built-in defaults - the model's standard effort level When to adjust effort * Bump up when the agent is giving shallow answers, missing edge cases, or producing incomplete implementations * Bump down when you need quick answers and don't want to wait for extended reasoning * Use max for security reviews, complex debugging sessions, or when you need the agent to consider many interacting constraints Related * Models - available models and their capabilities * Slash commands reference - quick command reference * Settings - all configurable settings Page updated: August 4, 2026 Available models How Kiro works