Skip to main content

​
What is Thinking Effort?

Happycapy gives you many models in the model selector. Some models also support Effort, which controls how much reasoning Happycapy should invest in the next task. If a model supports effort control, Happycapy shows the Effort option automatically in the model menu. You do not need to memorize which models support it. Currently, supported models include Sonnet, Opus, GLM, and DeepSeek V4 Pro models, and this list may change as model availability changes. Pick the model for the kind of work, then pick effort for how deeply Happycapy should work on it.

​
Where to Find It

Open the model selector beside the message box. Choose a model. If the model supports effort control, Happycapy shows an Effort row under the model list. Happycapy model selector showing the Effort row and the Low, Medium, High, Extra, Max, and Adaptive thinking controls The effort menu can include Low, Medium, High, Extra, Max, and Adaptive thinking. Some models show a default label next to one effort level. Use that as the recommended starting point for that model. You do not need to mention the effort level in your message. Set it in the model selector, then describe the task normally.

​
Choose Before a Long Task

For quick questions, changing models or effort is usually fine. For a long or complex task, choose the model and effort before you start. Try not to switch models or effort levels in the middle of the same complex task. Changing them can make Happycapy re-process more context, which may make the next step slower and use credits faster.

​
How to Choose Effort

Start with the default effort when you are unsure. Move up when the task is complex, important, or expensive to redo. Move down when speed and credits matter more than depth.

​
Use Adaptive Thinking

Adaptive thinking lets Happycapy spend less effort on simple requests and more effort on complex ones. Use it when:
  • the session mixes quick questions and deeper work
  • you are not sure how complex the task will become
  • you want Happycapy to decide when deeper reasoning is worth it
Adaptive thinking is still guided by the effort level you choose. A lower effort setting stays more conservative. A higher effort setting gives Happycapy more room to plan, inspect files, use tools, and check work.

​
What to Know

Higher effort usually gives Happycapy more room to plan, inspect files, use tools, and review results. It also usually takes longer and can use credits faster. Not every model supports effort control. If the model menu does not show Effort, use the model normally or choose another model that offers the setting.