Reasoning effort

Reasoning-capable models can think before they answer: better quality, slower and more expensive. max-thinking is one switch that decides whether each model thinks as hard as it is allowed to, or drops to a faster, lighter level.

One switch, two levels

max-thinkingEffect
onthe default: each model reasons up to its own tested ceiling
offfaster and cheaper: each model thinks minimally, or not at all where the model allows it

on reproduces the behaviour OpenCues has always had. off is the opt-in "go faster" mode.

What each model does at each level

Every verified model has a tested ceiling and a reduced level.

Provider and modelonoff
Cerebras gpt-oss-120bmediumlow
Groq gpt-oss-120b / 20blowlow
OpenAI gpt-5.4 familylownone
OpenRouter gpt-osslowlow
Cerebras zai-glm-4.7, gemma-4-31bnonenone
Anthropic, Geminino reasoning knob; the setting has no effect

Where on and off read the same, that is the model's floor: some providers reject a request to disable reasoning outright, so low is as low as they go.

What it affects

Every prose and lookup surface: word alternatives, sentence rewrites, _ fills, transforms, and agent rewrites. The settings classifier is the one exception; its output is tiny and must be dependable, so it pins low regardless of the switch, capped at whatever its model allows.

Three ways to set it

WhereHow
the filemax-thinking: off in ~/.cues/OPENCUES.md; picked up within about two seconds
the settings menuopencues settings _, cycle to max-thinking, Ctrl+Alt+Up/Down between on and off
plain wordstype think less _; the settings classifier routes it