Reasoning effort

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.

Available levels:

Not all models support every level. The picker only shows levels available for your current model. See reasoning configuration examples for common model schemas.

A model's configuration schema may also declare an internal default level. It is never offered as a choice, and a model that declares only default shows no picker at all, because there is nothing to choose between.

Each effort-capable model defines the values it accepts for reasoning-related fields in its configuration schema. The tables below show common schemas and are not an exhaustive support list. Use your surface's model and effort pickers to see the models and levels currently available to you.

In these examples, output_config.effort lists the available effort levels; thinking.type and thinking.display control reasoning behavior and visibility; and max_tokens sets the output length limit.

Claude examples use output_config.effort with thinking.type and thinking.display controls:

GPT-5.6 models use reasoning.effort:

GPT-5.6 models default to effort: "high".

Your effort choice in /model persists automatically. /effort <level> changes the current session only; run /effort set-current-as-default to save that level for the current model. In V3, --effort and --model apply only to the session Kiro starts with and aren't saved as defaults. Preferences are stored in ~/.kiro/settings/cli.json. See In-session settings for more on how preferences persist.

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):

{
  "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):

{
  "chat.modelDefaults": {
    "gpt-5.6-sol": {
      "reasoning": {
        "effort": "max"
      }
    },
    "gpt-5.6-terra": {
      "reasoning": {
        "effort": "low"
      }
    }
  }
}

Control whether the model uses extended thinking and how it displays reasoning:

{
  "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 on models that support that value. Claude Sonnet 5.5 uses between_tools instead of disabled; it applies the lowest thinking setting between tool calls and supports low, medium, and high effort.
• thinking.display - summarized shows a condensed version of reasoning; omitted hides it from output. Only applies when type is adaptive.

Set the maximum number of tokens the model can generate per response:

{
  "chat.modelDefaults": {
    "claude-opus-4.8": {
      "max_tokens": 128000
    },
    "claude-sonnet-4.6": {
      "max_tokens": 32000
    }
  }
}

Example max_tokens limits:

You can combine output_config, thinking, and max_tokens in a single model entry:

Claude example:

{
  "chat.modelDefaults": {
    "claude-opus-4.8": {
      "output_config": {
        "effort": "max"
      },
      "thinking": {
        "type": "adaptive",
        "display": "summarized"
      },
      "max_tokens": 128000
    }
  }
}

GPT-5.6 example:

{
  "chat.modelDefaults": {
    "gpt-5.6-sol": {
      "reasoning": {
        "effort": "max"
      },
      "max_tokens": 128000
    }
  }
}

To open your settings file in your editor:

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.

When determining the effort level for a session, Kiro applies this priority order:

1. Session override - value set via the Effort setting in /model, /effort <level>, or --effort during the current session. In V3, /clear keeps this value; /chat new starts from the saved defaults below
2. Workspace defaults - chat.modelDefaults in .kiro/settings/cli.json
3. User defaults - chat.modelDefaults in ~/.kiro/settings/cli.json
4. Built-in defaults - the model's standard effort level

• 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

• Models - available models and their capabilities
• Slash commands reference - quick command reference
• Settings - all configurable settings