> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ideatura.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Models and effort

> Compare model settings on a small representative task.

Choose from the models available in your account. The best choice for a task is the one that reaches an acceptable result with reasonable total effort.

<h2 id="separate-the-controls">
  1\. Separate the controls
</h2>

The AI model, thinking level, execution mode and connected document are different choices. A higher thinking level cannot correct a wrong target or missing reference. See [Conversation controls](/studio-reference/ui-conversation#ai-models).

<img src="https://mintcdn.com/ideatura/es2pEmCgfCrT5MoG/images/studio-tour/task-controls.svg?fit=max&auto=format&n=es2pEmCgfCrT5MoG&q=85&s=93af07a25dfe72037f7b2058be64ca9e" className="w-full h-auto mx-auto" alt="Separate conversation controls: 1 AI model; 2 execution mode; 3 connected apps. The example has No apps selected." width="1449" height="873" data-path="images/studio-tour/task-controls.svg" />

<h2 id="compare-the-same-task">
  2\. Compare the same task
</h2>

Open the model selector and choose from the current menu. Check the thinking level beside the model before sending; available models and credit estimates can change.

<img src="https://mintcdn.com/ideatura/DKUuEVCBA0vRk1xi/images/setup/models.svg?fit=max&auto=format&n=DKUuEVCBA0vRk1xi&q=85&s=2da00ea1648159dcdd6e299f34bc6166" className="w-full h-auto mx-auto" alt="Example model menu: 1 model selector; 2 thinking level. GPT-6.1 Sol with medium effort is selected; available models and credit estimates can change." width="1449" height="1221" data-path="images/setup/models.svg" />

Keep input, scope and acceptance checks fixed. Record the chosen model, thinking level, elapsed time, credits, retries and corrections. Include native inspection when judging quality.

<h2 id="use-the-result">
  3\. Use the result
</h2>

Choose settings from observed results rather than a universal cheapest-or-best ranking. Recheck when the task or available models change. Read [Credits](/help/credits) for usage and the existing [Models and credits reference](/ai/models-credits) for account indicators.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.